[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-739737427d52b833-mlx-frontier-ai-fully-on-device-on-apple-silicon-summary":3,"summaries-facets-categories":107,"summary-related-739737427d52b833-mlx-frontier-ai-fully-on-device-on-apple-silicon-summary":3693},{"id":4,"title":5,"ai":6,"body":13,"categories":64,"created_at":65,"date_modified":65,"description":58,"extension":66,"faq":65,"featured":67,"kicker_label":65,"meta":68,"navigation":86,"path":87,"published_at":88,"question":65,"scraped_at":89,"seo":90,"sitemap":91,"source_id":92,"source_name":93,"source_type":94,"source_url":95,"stem":96,"tags":97,"thumbnail_url":102,"tldr":103,"tweet":104,"unknown_tags":105,"__hash__":106},"summaries\u002Fsummaries\u002F739737427d52b833-mlx-frontier-ai-fully-on-device-on-apple-silicon-summary.md","MLX: Frontier AI Fully On-Device on Apple Silicon",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","x-ai\u002Fgrok-4.1-fast",7440,1795,22229,0.002363,{"type":14,"value":15,"toc":57},"minimark",[16,21,25,33,37,44,47,51,54],[17,18,20],"h2",{"id":19},"offload-ai-to-device-for-reliability-and-accessibility","Offload AI to Device for Reliability and Accessibility",[22,23,24],"p",{},"Cloud AI fails in unreliable networks like Africa or for always-on agents\u002Frobots—on-device compute solves this. MLX, an array framework like PyTorch for Apple Silicon, delivers: 1.5M downloads, 4,000+ ported models, day-zero support for Gemma 4. Run 426B-param models on M1 MacBooks\u002FiPhones at reasonable speeds using community optimizations. Motivation: Blind users regain vision\u002Fnavigation via phone cameras (e.g., MLX VLM describes scenes in real-time). Modular pipelines let you swap ASR (e.g., Whisper), LLM, TTS models to fit any Apple Silicon hardware, from M1 to latest.",[22,26,27,28,32],{},"Real-time vision: ",[29,30,31],"code",{},"mlxvlm run rfdeye"," detects objects (glasses as \"wine glass\") offline, even with internet off. Background blur + object detection for meetings uses native segmentation. Audio: Marvvis TTS generates speech in \u003C100ms; speech-to-speech chains STT → LLM → TTS for Jarvis-like control (\"blur a command\"). Supports Python\u002FSwift for native apps.",[17,34,36],{"id":35},"multimodal-omni-models-and-large-scale-inference","Multimodal Omni Models and Large-Scale Inference",[22,38,39,40,43],{},"Omni models (Gemma 4 E2\u002FE4, Qwen 2.5 Omni ~30B params) ingest image\u002Faudio\u002Ftext combos. ",[29,41,42],{},"mlxvlm ui gemma-2-27b"," analyzes images offline (e.g., describes speaker's profile pic with bio details) on 96GB VRAM machines—run all demos simultaneously. Parallelize hundreds of images\u002Fdocuments. Speech-to-speech sounds natural; build via prompt-cloud-code (e.g., replicate Whisperflow in 10min).",[22,45,46],{},"Monitor with Mactop (GPU\u002FCPU overlay)—inference spikes GPU usage. Avoid CoreML for now (private API issues); MLX uses GPU. Expect open-source to match GPT-4o\u002FClaude 3.5 Opus in 6 months—adjust UX to current speeds.",[17,48,50],{"id":49},"turbo-quant-and-community-projects-push-boundaries","Turbo Quant and Community Projects Push Boundaries",[22,52,53],{},"Turbo Quant (speaker's impl. 30min post-paper) quantizes KV cache 4x (1GB → 250MB), doubles throughput at 300k contexts, enables 1M-token contexts on-device with exact-match quality. Chained video gen on 16GB VRAM creates coherent stories from prompts (not one-shot). Community: Grounded reasoning (detect fires\u002Fitems in dashcams\u002Fsecurity cams); native voice apps (Locally reads text with MLX Audio\u002FMarvvis); robots (Rechi Mini with real-time Jarvis voice clone, MLX vision\u002Faudio for see\u002Fhear\u002Frespond).",[22,55,56],{},"Build agents that hear\u002Fsee\u002Fsound like humans on iPhone\u002FiPad\u002FMac\u002Frobot—no cloud calls. Share: Reshare community videos via speaker's X (@Prince_Canuma).",{"title":58,"searchDepth":59,"depth":59,"links":60},"",2,[61,62,63],{"id":19,"depth":59,"text":20},{"id":35,"depth":59,"text":36},{"id":49,"depth":59,"text":50},[],null,"md",false,{"content_references":69,"triage":81},[70,74,77],{"type":71,"title":72,"context":73},"tool","MLX","recommended",{"type":71,"title":75,"author":76,"context":73},"Mactop","Carson",{"type":78,"title":79,"context":80},"other","Turbo Quant","cited",{"relevance":82,"novelty":83,"quality":83,"actionability":82,"composite":84,"reasoning":85},3,4,3.45,"Category: AI & LLMs. The article discusses the MLX framework for on-device AI, which is relevant to AI engineering and addresses the need for reliable AI in low-connectivity areas. It presents novel insights into how on-device models can operate efficiently, but while it provides some practical applications, it lacks detailed step-by-step guidance for implementation.",true,"\u002Fsummaries\u002F739737427d52b833-mlx-frontier-ai-fully-on-device-on-apple-silicon-summary","2026-05-11 13:00:06","2026-05-11 15:00:18",{"title":5,"description":58},{"loc":87},"739737427d52b833","AI Engineer","video","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=zTLJNHj0DeQ","summaries\u002F739737427d52b833-mlx-frontier-ai-fully-on-device-on-apple-silicon-summary",[98,99,100,101],"mlx","on-device-ai","apple-silicon","multimodal-models","https:\u002F\u002Fi.ytimg.com\u002Fvi\u002FzTLJNHj0DeQ\u002Fhqdefault.jpg","MLX runs real-time vision, \u003C100ms TTS, omni models, 426B LLMs, and text-to-video on 16GB Mac VRAM—no cloud. Turbo Quant cuts KV cache 4x for 1M contexts, enabling accessibility and robots in low-connectivity areas.","[Prince Canuma](https:\u002F\u002Fx.com\u002FPrince_Canuma)'s conference talk demos MLX on Apple Silicon for on-device AI: real-time vision description, speech-to-speech pipelines, multimodal omni models, local Gemma runs, video generation on 16GB VRAM, Turbo Quant for 1M context, plus community voice apps and robots—all motivated by offline accessibility needs.",[98,99,100,101],"qM3J0TZNDoPzITNqInIVO1UVbgUV0UMQeFE6XiRvPSU",[108,111,114,117,120,123,125,127,129,131,133,135,138,140,142,144,146,148,150,152,154,156,159,162,164,166,169,171,173,176,178,180,182,184,186,188,190,192,194,196,198,200,202,204,206,208,210,212,214,216,218,220,222,224,226,228,230,232,234,236,238,240,242,244,246,248,250,252,254,256,258,260,262,264,266,268,270,272,274,276,278,280,282,284,286,288,290,292,294,296,298,300,302,304,306,308,310,312,314,316,318,320,322,324,326,328,330,332,334,336,338,340,342,344,346,348,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,433,435,437,439,441,443,445,447,449,451,453,455,457,459,461,463,465,467,469,471,473,475,477,479,481,483,485,487,489,491,493,495,497,499,501,503,505,507,509,511,513,515,517,519,521,523,525,527,529,531,533,535,537,539,541,543,545,547,549,551,553,555,557,559,561,563,565,567,569,571,573,575,577,579,581,583,585,587,589,591,593,595,597,599,601,603,605,607,609,611,613,615,617,619,621,623,625,627,629,631,633,635,637,639,641,643,645,647,649,651,653,655,657,659,661,663,665,667,669,671,673,675,677,679,681,683,685,687,689,691,693,695,697,699,701,703,705,707,709,711,713,715,717,719,721,723,725,727,729,731,733,735,737,739,741,743,745,747,749,751,753,755,757,759,761,763,765,767,769,771,773,775,777,779,781,783,785,787,789,791,793,795,797,799,801,803,805,807,809,811,813,815,817,819,821,823,825,827,829,831,833,835,837,839,841,843,845,847,849,851,853,855,857,859,861,863,865,867,869,871,873,875,877,879,881,883,885,887,889,891,893,895,897,899,901,903,905,907,909,911,913,915,917,919,921,923,925,927,929,931,933,935,937,939,941,943,945,947,949,951,953,955,957,959,961,963,965,967,969,971,973,975,977,979,981,983,985,987,989,991,993,995,997,999,1001,1003,1005,1007,1009,1011,1013,1015,1017,1019,1021,1023,1025,1027,1029,1031,1033,1035,1037,1039,1041,1043,1045,1047,1049,1051,1053,1055,1057,1059,1061,1063,1065,1067,1069,1071,1073,1075,1077,1079,1081,1083,1085,1087,1089,1091,1093,1095,1097,1099,1101,1103,1105,1107,1109,1111,1113,1115,1117,1119,1121,1123,1125,1127,1129,1131,1133,1135,1137,1139,1141,1143,1145,1147,1149,1151,1153,1155,1157,1159,1161,1163,1165,1167,1169,1171,1173,1175,1177,1179,1181,1183,1185,1187,1189,1191,1193,1195,1197,1199,1201,1203,1205,1207,1209,1211,1213,1215,1217,1219,1221,1223,1225,1227,1229,1231,1233,1235,1237,1239,1241,1243,1245,1247,1249,1251,1253,1255,1257,1259,1261,1263,1265,1267,1269,1271,1273,1275,1277,1279,1281,1283,1285,1287,1289,1291,1293,1295,1297,1299,1301,1303,1305,1307,1309,1311,1313,1315,1317,1319,1321,1323,1325,1327,1329,1331,1333,1335,1337,1339,1341,1343,1345,1347,1349,1351,1353,1355,1357,1359,1361,1363,1365,1367,1369,1371,1373,1375,1377,1379,1381,1383,1385,1387,1389,1391,1393,1395,1397,1399,1401,1403,1405,1407,1409,1411,1413,1415,1417,1419,1421,1423,1425,1427,1429,1431,1433,1435,1437,1439,1441,1443,1445,1447,1449,1451,1453,1455,1457,1459,1461,1463,1465,1467,1469,1471,1473,1475,1477,1479,1481,1483,1485,1487,1489,1491,1493,1495,1497,1499,1501,1503,1505,1507,1509,1511,1513,1515,1517,1519,1521,1523,1525,1527,1529,1531,1533,1535,1537,1539,1541,1543,1545,1547,1549,1551,1553,1555,1557,1559,1561,1563,1565,1567,1569,1571,1573,1575,1577,1579,1581,1583,1585,1587,1589,1591,1593,1595,1597,1599,1601,1603,1605,1607,1609,1611,1613,1615,1617,1619,1621,1623,1625,1627,1629,1631,1633,1635,1637,1639,1641,1643,1645,1647,1649,1651,1653,1655,1657,1659,1661,1663,1665,1667,1669,1671,1673,1675,1677,1679,1681,1683,1685,1687,1689,1691,1693,1695,1697,1699,1701,1703,1705,1707,1709,1711,1713,1715,1717,1719,1721,1723,1725,1727,1729,1731,1733,1735,1737,1739,1741,1743,1745,1747,1749,1751,1753,1755,1757,1759,1761,1763,1765,1767,1769,1771,1773,1775,1777,1779,1781,1783,1785,1787,1789,1791,1793,1795,1797,1799,1801,1803,1805,1807,1809,1811,1813,1815,1817,1819,1821,1823,1825,1827,1829,1831,1833,1835,1837,1839,1841,1843,1845,1847,1849,1851,1853,1855,1857,1859,1861,1863,1865,1867,1869,1871,1873,1875,1877,1879,1881,1883,1885,1887,1889,1891,1893,1895,1897,1899,1901,1903,1905,1907,1909,1911,1913,1915,1917,1919,1921,1923,1925,1927,1929,1931,1933,1935,1937,1939,1941,1943,1945,1947,1949,1951,1953,1955,1957,1959,1961,1963,1965,1967,1969,1971,1973,1975,1977,1979,1981,1983,1985,1987,1989,1991,1993,1995,1997,1999,2001,2003,2005,2007,2009,2011,2013,2015,2017,2019,2021,2023,2025,2027,2029,2031,2033,2035,2037,2039,2041,2043,2045,2047,2049,2051,2053,2055,2057,2059,2061,2063,2065,2067,2069,2071,2073,2075,2077,2079,2081,2083,2085,2087,2089,2091,2093,2095,2097,2099,2101,2103,2105,2107,2109,2111,2113,2115,2117,2119,2121,2123,2125,2127,2129,2131,2133,2135,2137,2139,2141,2143,2145,2147,2149,2151,2153,2155,2157,2159,2161,2163,2165,2167,2169,2171,2173,2175,2177,2179,2181,2183,2185,2187,2189,2191,2193,2195,2197,2199,2201,2203,2205,2207,2209,2211,2213,2215,2217,2219,2221,2223,2225,2227,2229,2231,2233,2235,2237,2239,2241,2243,2245,2247,2249,2251,2253,2255,2257,2259,2261,2263,2265,2267,2269,2271,2273,2275,2277,2279,2281,2283,2285,2287,2289,2291,2293,2295,2297,2299,2301,2303,2305,2307,2309,2311,2313,2315,2317,2319,2321,2323,2325,2327,2329,2331,2333,2335,2337,2339,2341,2343,2345,2347,2349,2351,2353,2355,2357,2359,2361,2363,2365,2367,2369,2371,2373,2375,2377,2379,2381,2383,2385,2387,2389,2391,2393,2395,2397,2399,2401,2403,2405,2407,2409,2411,2413,2415,2417,2419,2421,2423,2425,2427,2429,2431,2433,2435,2437,2439,2441,2443,2445,2447,2449,2451,2453,2455,2457,2459,2461,2463,2465,2467,2469,2471,2473,2475,2477,2479,2481,2483,2485,2487,2489,2491,2493,2495,2497,2499,2501,2503,2505,2507,2509,2511,2513,2515,2517,2519,2521,2523,2525,2527,2529,2531,2533,2535,2537,2539,2541,2543,2545,2547,2549,2551,2553,2555,2557,2559,2561,2563,2565,2567,2569,2571,2573,2575,2577,2579,2581,2583,2585,2587,2589,2591,2593,2595,2597,2599,2601,2603,2605,2607,2609,2611,2613,2615,2617,2619,2621,2623,2625,2627,2629,2631,2633,2635,2637,2639,2641,2643,2645,2647,2649,2651,2653,2655,2657,2659,2661,2663,2665,2667,2669,2671,2673,2675,2677,2679,2681,2683,2685,2687,2689,2691,2693,2695,2697,2699,2701,2703,2705,2707,2709,2711,2713,2715,2717,2719,2721,2723,2725,2727,2729,2731,2733,2735,2737,2739,2741,2743,2745,2747,2749,2751,2753,2755,2757,2759,2761,2763,2765,2767,2769,2771,2773,2775,2777,2779,2781,2783,2785,2787,2789,2791,2793,2795,2797,2799,2801,2803,2805,2807,2809,2811,2813,2815,2817,2819,2821,2823,2825,2827,2829,2831,2833,2835,2837,2839,2841,2843,2845,2847,2849,2851,2853,2855,2857,2859,2861,2863,2865,2867,2869,2871,2873,2875,2877,2879,2881,2883,2885,2887,2889,2891,2893,2895,2897,2899,2901,2903,2905,2907,2909,2911,2913,2915,2917,2919,2921,2923,2925,2927,2929,2931,2933,2935,2937,2939,2941,2943,2945,2947,2949,2951,2953,2955,2957,2959,2961,2963,2965,2967,2969,2971,2973,2975,2977,2979,2981,2983,2985,2987,2989,2991,2993,2995,2997,2999,3001,3003,3005,3007,3009,3011,3013,3015,3017,3019,3021,3023,3025,3027,3029,3031,3033,3035,3037,3039,3041,3043,3045,3047,3049,3051,3053,3055,3057,3059,3061,3063,3065,3067,3069,3071,3073,3075,3077,3079,3081,3083,3085,3087,3089,3091,3093,3095,3097,3099,3101,3103,3105,3107,3109,3111,3113,3115,3117,3119,3121,3123,3125,3127,3129,3131,3133,3135,3137,3139,3141,3143,3145,3147,3149,3151,3153,3155,3157,3159,3161,3163,3165,3167,3169,3171,3173,3175,3177,3179,3181,3183,3185,3187,3189,3191,3193,3195,3197,3199,3201,3203,3205,3207,3209,3211,3213,3215,3217,3219,3221,3223,3225,3227,3229,3231,3233,3235,3237,3239,3241,3243,3245,3247,3249,3251,3253,3255,3257,3259,3261,3263,3265,3267,3269,3271,3273,3275,3277,3279,3281,3283,3285,3287,3289,3291,3293,3295,3297,3299,3301,3303,3305,3307,3309,3311,3313,3315,3317,3319,3321,3323,3325,3327,3329,3331,3333,3335,3337,3339,3341,3343,3345,3347,3349,3351,3353,3355,3357,3359,3361,3363,3365,3367,3369,3371,3373,3375,3377,3379,3381,3383,3385,3387,3389,3391,3393,3395,3397,3399,3401,3403,3405,3407,3409,3411,3413,3415,3417,3419,3421,3423,3425,3427,3429,3431,3433,3435,3437,3439,3441,3443,3445,3447,3449,3451,3453,3455,3457,3459,3461,3463,3465,3467,3469,3471,3473,3475,3477,3479,3481,3483,3485,3487,3489,3491,3493,3495,3497,3499,3501,3503,3505,3507,3509,3511,3513,3515,3517,3519,3521,3523,3525,3527,3529,3531,3533,3535,3537,3539,3541,3543,3545,3547,3549,3551,3553,3555,3557,3559,3561,3563,3565,3567,3569,3571,3573,3575,3577,3579,3581,3583,3585,3587,3589,3591,3593,3595,3597,3599,3601,3603,3605,3607,3609,3611,3613,3615,3617,3619,3621,3623,3625,3627,3629,3631,3633,3635,3637,3639,3641,3643,3645,3647,3649,3651,3653,3655,3657,3659,3661,3663,3665,3667,3669,3671,3673,3675,3677,3679,3681,3683,3685,3687,3689,3691],{"categories":109},[110],"Developer Productivity",{"categories":112},[113],"Business & SaaS",{"categories":115},[116],"AI & LLMs",{"categories":118},[119],"AI Automation",{"categories":121},[122],"Product Strategy",{"categories":124},[116],{"categories":126},[110],{"categories":128},[113],{"categories":130},[],{"categories":132},[116],{"categories":134},[],{"categories":136},[137],"AI News & Trends",{"categories":139},[119],{"categories":141},[137],{"categories":143},[119],{"categories":145},[119],{"categories":147},[116],{"categories":149},[116],{"categories":151},[137],{"categories":153},[116],{"categories":155},[],{"categories":157},[158],"Design & Frontend",{"categories":160},[161],"Data Science & Visualization",{"categories":163},[137],{"categories":165},[],{"categories":167},[168],"Software Engineering",{"categories":170},[116],{"categories":172},[119],{"categories":174},[175],"Marketing & Growth",{"categories":177},[116],{"categories":179},[119],{"categories":181},[],{"categories":183},[],{"categories":185},[158],{"categories":187},[119],{"categories":189},[110],{"categories":191},[158],{"categories":193},[116],{"categories":195},[119],{"categories":197},[137],{"categories":199},[],{"categories":201},[],{"categories":203},[119],{"categories":205},[168],{"categories":207},[],{"categories":209},[113],{"categories":211},[],{"categories":213},[],{"categories":215},[119],{"categories":217},[119],{"categories":219},[116],{"categories":221},[],{"categories":223},[168],{"categories":225},[],{"categories":227},[],{"categories":229},[],{"categories":231},[116],{"categories":233},[175],{"categories":235},[158],{"categories":237},[158],{"categories":239},[116],{"categories":241},[119],{"categories":243},[116],{"categories":245},[116],{"categories":247},[119],{"categories":249},[119],{"categories":251},[161],{"categories":253},[137],{"categories":255},[119],{"categories":257},[175],{"categories":259},[119],{"categories":261},[122],{"categories":263},[],{"categories":265},[119],{"categories":267},[],{"categories":269},[119],{"categories":271},[168],{"categories":273},[158],{"categories":275},[116],{"categories":277},[],{"categories":279},[],{"categories":281},[119],{"categories":283},[],{"categories":285},[116],{"categories":287},[],{"categories":289},[110],{"categories":291},[168],{"categories":293},[113],{"categories":295},[137],{"categories":297},[116],{"categories":299},[],{"categories":301},[116],{"categories":303},[],{"categories":305},[168],{"categories":307},[161],{"categories":309},[],{"categories":311},[116],{"categories":313},[158],{"categories":315},[],{"categories":317},[158],{"categories":319},[119],{"categories":321},[],{"categories":323},[119],{"categories":325},[137],{"categories":327},[113],{"categories":329},[116],{"categories":331},[],{"categories":333},[119],{"categories":335},[116],{"categories":337},[122],{"categories":339},[],{"categories":341},[116],{"categories":343},[119],{"categories":345},[119],{"categories":347},[],{"categories":349},[161],{"categories":351},[116],{"categories":353},[],{"categories":355},[110],{"categories":357},[113],{"categories":359},[116],{"categories":361},[119],{"categories":363},[168],{"categories":365},[116],{"categories":367},[],{"categories":369},[],{"categories":371},[116],{"categories":373},[],{"categories":375},[158],{"categories":377},[],{"categories":379},[116],{"categories":381},[],{"categories":383},[119],{"categories":385},[116],{"categories":387},[158],{"categories":389},[],{"categories":391},[116],{"categories":393},[116],{"categories":395},[113],{"categories":397},[119],{"categories":399},[116],{"categories":401},[158],{"categories":403},[119],{"categories":405},[],{"categories":407},[],{"categories":409},[137],{"categories":411},[],{"categories":413},[116],{"categories":415},[113,175],{"categories":417},[],{"categories":419},[116],{"categories":421},[],{"categories":423},[],{"categories":425},[116],{"categories":427},[],{"categories":429},[116],{"categories":431},[432],"DevOps & Cloud",{"categories":434},[],{"categories":436},[137],{"categories":438},[158],{"categories":440},[],{"categories":442},[137],{"categories":444},[137],{"categories":446},[116],{"categories":448},[175],{"categories":450},[],{"categories":452},[113],{"categories":454},[],{"categories":456},[116,432],{"categories":458},[116],{"categories":460},[116],{"categories":462},[119],{"categories":464},[116,168],{"categories":466},[161],{"categories":468},[116],{"categories":470},[175],{"categories":472},[119],{"categories":474},[119],{"categories":476},[],{"categories":478},[119],{"categories":480},[116,113],{"categories":482},[],{"categories":484},[158],{"categories":486},[158],{"categories":488},[],{"categories":490},[],{"categories":492},[137],{"categories":494},[],{"categories":496},[110],{"categories":498},[168],{"categories":500},[116],{"categories":502},[158],{"categories":504},[119],{"categories":506},[168],{"categories":508},[137],{"categories":510},[158],{"categories":512},[],{"categories":514},[116],{"categories":516},[116],{"categories":518},[116],{"categories":520},[137],{"categories":522},[110],{"categories":524},[116],{"categories":526},[119],{"categories":528},[432],{"categories":530},[158],{"categories":532},[119],{"categories":534},[],{"categories":536},[],{"categories":538},[158],{"categories":540},[137],{"categories":542},[161],{"categories":544},[],{"categories":546},[116],{"categories":548},[116],{"categories":550},[113],{"categories":552},[116],{"categories":554},[116],{"categories":556},[137],{"categories":558},[],{"categories":560},[119],{"categories":562},[168],{"categories":564},[],{"categories":566},[116],{"categories":568},[116],{"categories":570},[119],{"categories":572},[],{"categories":574},[],{"categories":576},[116],{"categories":578},[],{"categories":580},[113],{"categories":582},[119],{"categories":584},[],{"categories":586},[110],{"categories":588},[116],{"categories":590},[113],{"categories":592},[137],{"categories":594},[],{"categories":596},[],{"categories":598},[],{"categories":600},[137],{"categories":602},[137],{"categories":604},[],{"categories":606},[],{"categories":608},[113],{"categories":610},[],{"categories":612},[],{"categories":614},[110],{"categories":616},[],{"categories":618},[175],{"categories":620},[119],{"categories":622},[113],{"categories":624},[119],{"categories":626},[168],{"categories":628},[],{"categories":630},[122],{"categories":632},[158],{"categories":634},[168],{"categories":636},[116],{"categories":638},[119],{"categories":640},[113],{"categories":642},[116],{"categories":644},[],{"categories":646},[],{"categories":648},[168],{"categories":650},[161],{"categories":652},[122],{"categories":654},[119],{"categories":656},[116],{"categories":658},[],{"categories":660},[432],{"categories":662},[],{"categories":664},[119],{"categories":666},[],{"categories":668},[],{"categories":670},[116],{"categories":672},[158],{"categories":674},[175],{"categories":676},[119],{"categories":678},[],{"categories":680},[110],{"categories":682},[],{"categories":684},[137],{"categories":686},[116,432],{"categories":688},[137],{"categories":690},[116],{"categories":692},[113],{"categories":694},[116],{"categories":696},[],{"categories":698},[113],{"categories":700},[],{"categories":702},[168],{"categories":704},[158],{"categories":706},[137],{"categories":708},[161],{"categories":710},[110],{"categories":712},[116],{"categories":714},[168],{"categories":716},[],{"categories":718},[],{"categories":720},[122],{"categories":722},[],{"categories":724},[116],{"categories":726},[],{"categories":728},[158],{"categories":730},[158],{"categories":732},[158],{"categories":734},[],{"categories":736},[],{"categories":738},[137],{"categories":740},[119],{"categories":742},[116],{"categories":744},[116],{"categories":746},[116],{"categories":748},[113],{"categories":750},[116],{"categories":752},[],{"categories":754},[168],{"categories":756},[168],{"categories":758},[113],{"categories":760},[],{"categories":762},[116],{"categories":764},[116],{"categories":766},[113],{"categories":768},[137],{"categories":770},[175],{"categories":772},[119],{"categories":774},[],{"categories":776},[158],{"categories":778},[],{"categories":780},[116],{"categories":782},[],{"categories":784},[113],{"categories":786},[119],{"categories":788},[],{"categories":790},[432],{"categories":792},[161],{"categories":794},[168],{"categories":796},[175],{"categories":798},[168],{"categories":800},[119],{"categories":802},[],{"categories":804},[],{"categories":806},[119],{"categories":808},[110],{"categories":810},[119],{"categories":812},[122],{"categories":814},[113],{"categories":816},[],{"categories":818},[116],{"categories":820},[122],{"categories":822},[116],{"categories":824},[116],{"categories":826},[175],{"categories":828},[158],{"categories":830},[119],{"categories":832},[],{"categories":834},[],{"categories":836},[432],{"categories":838},[168],{"categories":840},[],{"categories":842},[119],{"categories":844},[116],{"categories":846},[158,116],{"categories":848},[110],{"categories":850},[],{"categories":852},[116],{"categories":854},[110],{"categories":856},[158],{"categories":858},[119],{"categories":860},[168],{"categories":862},[],{"categories":864},[116],{"categories":866},[],{"categories":868},[110],{"categories":870},[],{"categories":872},[119],{"categories":874},[122],{"categories":876},[116],{"categories":878},[116],{"categories":880},[158],{"categories":882},[119],{"categories":884},[432],{"categories":886},[158],{"categories":888},[119],{"categories":890},[116],{"categories":892},[116],{"categories":894},[116],{"categories":896},[137],{"categories":898},[],{"categories":900},[122],{"categories":902},[119],{"categories":904},[158],{"categories":906},[119],{"categories":908},[168],{"categories":910},[158],{"categories":912},[119],{"categories":914},[137],{"categories":916},[],{"categories":918},[116],{"categories":920},[158],{"categories":922},[116],{"categories":924},[110],{"categories":926},[137],{"categories":928},[116],{"categories":930},[175],{"categories":932},[116],{"categories":934},[116],{"categories":936},[119],{"categories":938},[119],{"categories":940},[116],{"categories":942},[119],{"categories":944},[158],{"categories":946},[116],{"categories":948},[],{"categories":950},[],{"categories":952},[168],{"categories":954},[],{"categories":956},[110],{"categories":958},[432],{"categories":960},[],{"categories":962},[110],{"categories":964},[113],{"categories":966},[175],{"categories":968},[],{"categories":970},[113],{"categories":972},[],{"categories":974},[],{"categories":976},[],{"categories":978},[],{"categories":980},[],{"categories":982},[116],{"categories":984},[119],{"categories":986},[432],{"categories":988},[110],{"categories":990},[116],{"categories":992},[168],{"categories":994},[122],{"categories":996},[116],{"categories":998},[175],{"categories":1000},[116],{"categories":1002},[116],{"categories":1004},[116],{"categories":1006},[116,110],{"categories":1008},[168],{"categories":1010},[168],{"categories":1012},[158],{"categories":1014},[116],{"categories":1016},[],{"categories":1018},[],{"categories":1020},[],{"categories":1022},[168],{"categories":1024},[161],{"categories":1026},[137],{"categories":1028},[158],{"categories":1030},[],{"categories":1032},[116],{"categories":1034},[116],{"categories":1036},[],{"categories":1038},[],{"categories":1040},[119],{"categories":1042},[116],{"categories":1044},[113],{"categories":1046},[],{"categories":1048},[110],{"categories":1050},[116],{"categories":1052},[110],{"categories":1054},[116],{"categories":1056},[168],{"categories":1058},[175],{"categories":1060},[116,158],{"categories":1062},[137],{"categories":1064},[158],{"categories":1066},[],{"categories":1068},[432],{"categories":1070},[158],{"categories":1072},[119],{"categories":1074},[],{"categories":1076},[],{"categories":1078},[],{"categories":1080},[],{"categories":1082},[168],{"categories":1084},[119],{"categories":1086},[119],{"categories":1088},[432],{"categories":1090},[116],{"categories":1092},[116],{"categories":1094},[116],{"categories":1096},[],{"categories":1098},[158],{"categories":1100},[],{"categories":1102},[],{"categories":1104},[119],{"categories":1106},[],{"categories":1108},[],{"categories":1110},[175],{"categories":1112},[175],{"categories":1114},[119],{"categories":1116},[],{"categories":1118},[116],{"categories":1120},[116],{"categories":1122},[168],{"categories":1124},[158],{"categories":1126},[158],{"categories":1128},[119],{"categories":1130},[110],{"categories":1132},[116],{"categories":1134},[158],{"categories":1136},[158],{"categories":1138},[119],{"categories":1140},[119],{"categories":1142},[116],{"categories":1144},[],{"categories":1146},[],{"categories":1148},[116],{"categories":1150},[119],{"categories":1152},[137],{"categories":1154},[168],{"categories":1156},[110],{"categories":1158},[116],{"categories":1160},[],{"categories":1162},[119],{"categories":1164},[119],{"categories":1166},[],{"categories":1168},[110],{"categories":1170},[116],{"categories":1172},[110],{"categories":1174},[110],{"categories":1176},[],{"categories":1178},[],{"categories":1180},[119],{"categories":1182},[119],{"categories":1184},[116],{"categories":1186},[116],{"categories":1188},[137],{"categories":1190},[161],{"categories":1192},[122],{"categories":1194},[137],{"categories":1196},[158],{"categories":1198},[],{"categories":1200},[137],{"categories":1202},[],{"categories":1204},[],{"categories":1206},[],{"categories":1208},[],{"categories":1210},[168],{"categories":1212},[161],{"categories":1214},[],{"categories":1216},[116],{"categories":1218},[116],{"categories":1220},[161],{"categories":1222},[168],{"categories":1224},[],{"categories":1226},[],{"categories":1228},[119],{"categories":1230},[137],{"categories":1232},[137],{"categories":1234},[119],{"categories":1236},[110],{"categories":1238},[116,432],{"categories":1240},[],{"categories":1242},[158],{"categories":1244},[110],{"categories":1246},[119],{"categories":1248},[158],{"categories":1250},[],{"categories":1252},[119],{"categories":1254},[119],{"categories":1256},[116],{"categories":1258},[175],{"categories":1260},[168],{"categories":1262},[158],{"categories":1264},[],{"categories":1266},[119],{"categories":1268},[116],{"categories":1270},[119],{"categories":1272},[119],{"categories":1274},[119],{"categories":1276},[175],{"categories":1278},[119],{"categories":1280},[116],{"categories":1282},[],{"categories":1284},[175],{"categories":1286},[137],{"categories":1288},[119],{"categories":1290},[],{"categories":1292},[],{"categories":1294},[116],{"categories":1296},[119],{"categories":1298},[137],{"categories":1300},[119],{"categories":1302},[],{"categories":1304},[],{"categories":1306},[],{"categories":1308},[119],{"categories":1310},[],{"categories":1312},[],{"categories":1314},[161],{"categories":1316},[116],{"categories":1318},[161],{"categories":1320},[137],{"categories":1322},[116],{"categories":1324},[116],{"categories":1326},[119],{"categories":1328},[116],{"categories":1330},[],{"categories":1332},[],{"categories":1334},[432],{"categories":1336},[],{"categories":1338},[],{"categories":1340},[110],{"categories":1342},[],{"categories":1344},[],{"categories":1346},[],{"categories":1348},[],{"categories":1350},[168],{"categories":1352},[137],{"categories":1354},[175],{"categories":1356},[113],{"categories":1358},[116],{"categories":1360},[116],{"categories":1362},[113],{"categories":1364},[],{"categories":1366},[158],{"categories":1368},[119],{"categories":1370},[113],{"categories":1372},[116],{"categories":1374},[116],{"categories":1376},[110],{"categories":1378},[],{"categories":1380},[110],{"categories":1382},[116],{"categories":1384},[175],{"categories":1386},[119],{"categories":1388},[137],{"categories":1390},[113],{"categories":1392},[116],{"categories":1394},[119],{"categories":1396},[],{"categories":1398},[116],{"categories":1400},[110],{"categories":1402},[116],{"categories":1404},[],{"categories":1406},[137],{"categories":1408},[116],{"categories":1410},[],{"categories":1412},[113],{"categories":1414},[116],{"categories":1416},[],{"categories":1418},[],{"categories":1420},[],{"categories":1422},[116],{"categories":1424},[],{"categories":1426},[432],{"categories":1428},[116],{"categories":1430},[],{"categories":1432},[116],{"categories":1434},[116],{"categories":1436},[116],{"categories":1438},[116,432],{"categories":1440},[116],{"categories":1442},[116],{"categories":1444},[158],{"categories":1446},[119],{"categories":1448},[],{"categories":1450},[119],{"categories":1452},[116],{"categories":1454},[116],{"categories":1456},[116],{"categories":1458},[110],{"categories":1460},[110],{"categories":1462},[168],{"categories":1464},[158],{"categories":1466},[119],{"categories":1468},[],{"categories":1470},[116],{"categories":1472},[137],{"categories":1474},[116],{"categories":1476},[113],{"categories":1478},[],{"categories":1480},[432],{"categories":1482},[158],{"categories":1484},[158],{"categories":1486},[119],{"categories":1488},[137],{"categories":1490},[119],{"categories":1492},[116],{"categories":1494},[],{"categories":1496},[116],{"categories":1498},[],{"categories":1500},[],{"categories":1502},[116],{"categories":1504},[116],{"categories":1506},[116],{"categories":1508},[119],{"categories":1510},[116],{"categories":1512},[],{"categories":1514},[161],{"categories":1516},[119],{"categories":1518},[],{"categories":1520},[],{"categories":1522},[116],{"categories":1524},[137],{"categories":1526},[],{"categories":1528},[158],{"categories":1530},[432],{"categories":1532},[137],{"categories":1534},[168],{"categories":1536},[168],{"categories":1538},[137],{"categories":1540},[137],{"categories":1542},[432],{"categories":1544},[],{"categories":1546},[137],{"categories":1548},[116],{"categories":1550},[110],{"categories":1552},[137],{"categories":1554},[],{"categories":1556},[161],{"categories":1558},[137],{"categories":1560},[168],{"categories":1562},[137],{"categories":1564},[432],{"categories":1566},[116],{"categories":1568},[116],{"categories":1570},[],{"categories":1572},[113],{"categories":1574},[],{"categories":1576},[],{"categories":1578},[116],{"categories":1580},[116],{"categories":1582},[116],{"categories":1584},[116],{"categories":1586},[],{"categories":1588},[161],{"categories":1590},[110],{"categories":1592},[],{"categories":1594},[116],{"categories":1596},[116],{"categories":1598},[432],{"categories":1600},[432],{"categories":1602},[],{"categories":1604},[119],{"categories":1606},[137],{"categories":1608},[137],{"categories":1610},[116],{"categories":1612},[119],{"categories":1614},[],{"categories":1616},[158],{"categories":1618},[116],{"categories":1620},[116],{"categories":1622},[],{"categories":1624},[],{"categories":1626},[432],{"categories":1628},[116],{"categories":1630},[168],{"categories":1632},[113],{"categories":1634},[116],{"categories":1636},[],{"categories":1638},[119],{"categories":1640},[110],{"categories":1642},[110],{"categories":1644},[],{"categories":1646},[116],{"categories":1648},[158],{"categories":1650},[119],{"categories":1652},[],{"categories":1654},[116],{"categories":1656},[116],{"categories":1658},[119],{"categories":1660},[],{"categories":1662},[119],{"categories":1664},[168],{"categories":1666},[],{"categories":1668},[116],{"categories":1670},[],{"categories":1672},[116],{"categories":1674},[],{"categories":1676},[116],{"categories":1678},[116],{"categories":1680},[],{"categories":1682},[116],{"categories":1684},[137],{"categories":1686},[116],{"categories":1688},[116],{"categories":1690},[110],{"categories":1692},[116],{"categories":1694},[137],{"categories":1696},[119],{"categories":1698},[],{"categories":1700},[116],{"categories":1702},[175],{"categories":1704},[],{"categories":1706},[],{"categories":1708},[],{"categories":1710},[110],{"categories":1712},[137],{"categories":1714},[119],{"categories":1716},[116],{"categories":1718},[158],{"categories":1720},[119],{"categories":1722},[],{"categories":1724},[119],{"categories":1726},[],{"categories":1728},[116],{"categories":1730},[119],{"categories":1732},[116],{"categories":1734},[],{"categories":1736},[116],{"categories":1738},[116],{"categories":1740},[137],{"categories":1742},[158],{"categories":1744},[119],{"categories":1746},[158],{"categories":1748},[113],{"categories":1750},[],{"categories":1752},[],{"categories":1754},[116],{"categories":1756},[110],{"categories":1758},[137],{"categories":1760},[],{"categories":1762},[],{"categories":1764},[168],{"categories":1766},[158],{"categories":1768},[],{"categories":1770},[116],{"categories":1772},[],{"categories":1774},[175],{"categories":1776},[116],{"categories":1778},[432],{"categories":1780},[168],{"categories":1782},[],{"categories":1784},[119],{"categories":1786},[116],{"categories":1788},[119],{"categories":1790},[119],{"categories":1792},[116],{"categories":1794},[],{"categories":1796},[110],{"categories":1798},[116],{"categories":1800},[113],{"categories":1802},[168],{"categories":1804},[158],{"categories":1806},[],{"categories":1808},[],{"categories":1810},[],{"categories":1812},[119],{"categories":1814},[158],{"categories":1816},[137],{"categories":1818},[116],{"categories":1820},[137],{"categories":1822},[158],{"categories":1824},[],{"categories":1826},[158],{"categories":1828},[137],{"categories":1830},[113],{"categories":1832},[116],{"categories":1834},[137],{"categories":1836},[175],{"categories":1838},[],{"categories":1840},[],{"categories":1842},[161],{"categories":1844},[116,168],{"categories":1846},[137],{"categories":1848},[116],{"categories":1850},[119],{"categories":1852},[119],{"categories":1854},[116],{"categories":1856},[],{"categories":1858},[168],{"categories":1860},[116],{"categories":1862},[161],{"categories":1864},[119],{"categories":1866},[175],{"categories":1868},[432],{"categories":1870},[],{"categories":1872},[110],{"categories":1874},[119],{"categories":1876},[119],{"categories":1878},[168],{"categories":1880},[116],{"categories":1882},[116],{"categories":1884},[],{"categories":1886},[],{"categories":1888},[],{"categories":1890},[432],{"categories":1892},[137],{"categories":1894},[116],{"categories":1896},[116],{"categories":1898},[116],{"categories":1900},[],{"categories":1902},[161],{"categories":1904},[113],{"categories":1906},[],{"categories":1908},[119],{"categories":1910},[432],{"categories":1912},[],{"categories":1914},[158],{"categories":1916},[158],{"categories":1918},[],{"categories":1920},[168],{"categories":1922},[158],{"categories":1924},[116],{"categories":1926},[],{"categories":1928},[137],{"categories":1930},[116],{"categories":1932},[158],{"categories":1934},[119],{"categories":1936},[137],{"categories":1938},[],{"categories":1940},[119],{"categories":1942},[158],{"categories":1944},[116],{"categories":1946},[],{"categories":1948},[116],{"categories":1950},[116],{"categories":1952},[432],{"categories":1954},[137],{"categories":1956},[161],{"categories":1958},[161],{"categories":1960},[],{"categories":1962},[],{"categories":1964},[],{"categories":1966},[119],{"categories":1968},[168],{"categories":1970},[168],{"categories":1972},[],{"categories":1974},[],{"categories":1976},[116],{"categories":1978},[],{"categories":1980},[119],{"categories":1982},[116],{"categories":1984},[],{"categories":1986},[116],{"categories":1988},[113],{"categories":1990},[116],{"categories":1992},[175],{"categories":1994},[119],{"categories":1996},[116],{"categories":1998},[168],{"categories":2000},[137],{"categories":2002},[119],{"categories":2004},[],{"categories":2006},[137],{"categories":2008},[119],{"categories":2010},[119],{"categories":2012},[],{"categories":2014},[113],{"categories":2016},[119],{"categories":2018},[],{"categories":2020},[116],{"categories":2022},[110],{"categories":2024},[137],{"categories":2026},[432],{"categories":2028},[119],{"categories":2030},[119],{"categories":2032},[110],{"categories":2034},[116],{"categories":2036},[],{"categories":2038},[],{"categories":2040},[158],{"categories":2042},[116,113],{"categories":2044},[],{"categories":2046},[110],{"categories":2048},[161],{"categories":2050},[116],{"categories":2052},[168],{"categories":2054},[116],{"categories":2056},[119],{"categories":2058},[116],{"categories":2060},[116],{"categories":2062},[137],{"categories":2064},[119],{"categories":2066},[],{"categories":2068},[],{"categories":2070},[119],{"categories":2072},[116],{"categories":2074},[432],{"categories":2076},[],{"categories":2078},[116],{"categories":2080},[119],{"categories":2082},[],{"categories":2084},[116],{"categories":2086},[175],{"categories":2088},[161],{"categories":2090},[119],{"categories":2092},[116],{"categories":2094},[432],{"categories":2096},[],{"categories":2098},[116],{"categories":2100},[175],{"categories":2102},[158],{"categories":2104},[116],{"categories":2106},[],{"categories":2108},[175],{"categories":2110},[137],{"categories":2112},[116],{"categories":2114},[116],{"categories":2116},[110],{"categories":2118},[],{"categories":2120},[],{"categories":2122},[158],{"categories":2124},[116],{"categories":2126},[161],{"categories":2128},[175],{"categories":2130},[175],{"categories":2132},[137],{"categories":2134},[],{"categories":2136},[],{"categories":2138},[116],{"categories":2140},[],{"categories":2142},[116,168],{"categories":2144},[137],{"categories":2146},[119],{"categories":2148},[168],{"categories":2150},[116],{"categories":2152},[110],{"categories":2154},[],{"categories":2156},[],{"categories":2158},[110],{"categories":2160},[175],{"categories":2162},[116],{"categories":2164},[],{"categories":2166},[158,116],{"categories":2168},[432],{"categories":2170},[110],{"categories":2172},[],{"categories":2174},[113],{"categories":2176},[113],{"categories":2178},[116],{"categories":2180},[168],{"categories":2182},[119],{"categories":2184},[137],{"categories":2186},[175],{"categories":2188},[158],{"categories":2190},[116],{"categories":2192},[116],{"categories":2194},[116],{"categories":2196},[110],{"categories":2198},[116],{"categories":2200},[119],{"categories":2202},[137],{"categories":2204},[],{"categories":2206},[],{"categories":2208},[161],{"categories":2210},[168],{"categories":2212},[116],{"categories":2214},[158],{"categories":2216},[161],{"categories":2218},[116],{"categories":2220},[116],{"categories":2222},[119],{"categories":2224},[119],{"categories":2226},[116,113],{"categories":2228},[],{"categories":2230},[158],{"categories":2232},[],{"categories":2234},[116],{"categories":2236},[137],{"categories":2238},[110],{"categories":2240},[110],{"categories":2242},[119],{"categories":2244},[116],{"categories":2246},[113],{"categories":2248},[168],{"categories":2250},[175],{"categories":2252},[],{"categories":2254},[137],{"categories":2256},[116],{"categories":2258},[116],{"categories":2260},[137],{"categories":2262},[168],{"categories":2264},[116],{"categories":2266},[119],{"categories":2268},[137],{"categories":2270},[116],{"categories":2272},[158],{"categories":2274},[116],{"categories":2276},[116],{"categories":2278},[432],{"categories":2280},[122],{"categories":2282},[119],{"categories":2284},[116],{"categories":2286},[137],{"categories":2288},[119],{"categories":2290},[175],{"categories":2292},[116],{"categories":2294},[],{"categories":2296},[116],{"categories":2298},[],{"categories":2300},[],{"categories":2302},[],{"categories":2304},[113],{"categories":2306},[116],{"categories":2308},[119],{"categories":2310},[137],{"categories":2312},[137],{"categories":2314},[137],{"categories":2316},[137],{"categories":2318},[],{"categories":2320},[110],{"categories":2322},[119],{"categories":2324},[137],{"categories":2326},[110],{"categories":2328},[119],{"categories":2330},[116],{"categories":2332},[116,119],{"categories":2334},[119],{"categories":2336},[432],{"categories":2338},[137],{"categories":2340},[137],{"categories":2342},[119],{"categories":2344},[116],{"categories":2346},[],{"categories":2348},[137],{"categories":2350},[175],{"categories":2352},[110],{"categories":2354},[116],{"categories":2356},[116],{"categories":2358},[],{"categories":2360},[168],{"categories":2362},[],{"categories":2364},[110],{"categories":2366},[119],{"categories":2368},[137],{"categories":2370},[116],{"categories":2372},[137],{"categories":2374},[110],{"categories":2376},[137],{"categories":2378},[137],{"categories":2380},[],{"categories":2382},[113],{"categories":2384},[119],{"categories":2386},[137],{"categories":2388},[137],{"categories":2390},[137],{"categories":2392},[137],{"categories":2394},[137],{"categories":2396},[137],{"categories":2398},[137],{"categories":2400},[137],{"categories":2402},[137],{"categories":2404},[137],{"categories":2406},[161],{"categories":2408},[110],{"categories":2410},[116],{"categories":2412},[116],{"categories":2414},[],{"categories":2416},[116,110],{"categories":2418},[],{"categories":2420},[119],{"categories":2422},[137],{"categories":2424},[119],{"categories":2426},[116],{"categories":2428},[116],{"categories":2430},[116],{"categories":2432},[116],{"categories":2434},[116],{"categories":2436},[119],{"categories":2438},[113],{"categories":2440},[158],{"categories":2442},[137],{"categories":2444},[116],{"categories":2446},[],{"categories":2448},[],{"categories":2450},[119],{"categories":2452},[158],{"categories":2454},[116],{"categories":2456},[],{"categories":2458},[],{"categories":2460},[175],{"categories":2462},[116],{"categories":2464},[],{"categories":2466},[],{"categories":2468},[110],{"categories":2470},[113],{"categories":2472},[116],{"categories":2474},[113],{"categories":2476},[158],{"categories":2478},[],{"categories":2480},[137],{"categories":2482},[],{"categories":2484},[158],{"categories":2486},[116],{"categories":2488},[175],{"categories":2490},[],{"categories":2492},[175],{"categories":2494},[],{"categories":2496},[],{"categories":2498},[119],{"categories":2500},[],{"categories":2502},[113],{"categories":2504},[110],{"categories":2506},[158],{"categories":2508},[168],{"categories":2510},[],{"categories":2512},[],{"categories":2514},[116],{"categories":2516},[110],{"categories":2518},[175],{"categories":2520},[],{"categories":2522},[119],{"categories":2524},[119],{"categories":2526},[137],{"categories":2528},[116],{"categories":2530},[119],{"categories":2532},[116],{"categories":2534},[119],{"categories":2536},[116],{"categories":2538},[122],{"categories":2540},[137],{"categories":2542},[],{"categories":2544},[175],{"categories":2546},[168],{"categories":2548},[119],{"categories":2550},[],{"categories":2552},[116],{"categories":2554},[119],{"categories":2556},[113],{"categories":2558},[110],{"categories":2560},[116],{"categories":2562},[158],{"categories":2564},[168],{"categories":2566},[168],{"categories":2568},[116],{"categories":2570},[161],{"categories":2572},[116],{"categories":2574},[119],{"categories":2576},[113],{"categories":2578},[119],{"categories":2580},[116],{"categories":2582},[116],{"categories":2584},[119],{"categories":2586},[137],{"categories":2588},[],{"categories":2590},[110],{"categories":2592},[116],{"categories":2594},[119],{"categories":2596},[116],{"categories":2598},[116],{"categories":2600},[],{"categories":2602},[158],{"categories":2604},[113],{"categories":2606},[137],{"categories":2608},[116],{"categories":2610},[116],{"categories":2612},[158],{"categories":2614},[175],{"categories":2616},[161],{"categories":2618},[116],{"categories":2620},[137],{"categories":2622},[116],{"categories":2624},[119],{"categories":2626},[432],{"categories":2628},[116],{"categories":2630},[119],{"categories":2632},[161],{"categories":2634},[],{"categories":2636},[119],{"categories":2638},[168],{"categories":2640},[158],{"categories":2642},[116],{"categories":2644},[110],{"categories":2646},[113],{"categories":2648},[168],{"categories":2650},[],{"categories":2652},[119],{"categories":2654},[116],{"categories":2656},[],{"categories":2658},[137],{"categories":2660},[],{"categories":2662},[137],{"categories":2664},[116],{"categories":2666},[119],{"categories":2668},[119],{"categories":2670},[119],{"categories":2672},[],{"categories":2674},[],{"categories":2676},[116],{"categories":2678},[116],{"categories":2680},[],{"categories":2682},[158],{"categories":2684},[119],{"categories":2686},[175],{"categories":2688},[110],{"categories":2690},[],{"categories":2692},[],{"categories":2694},[137],{"categories":2696},[168],{"categories":2698},[116],{"categories":2700},[116],{"categories":2702},[116],{"categories":2704},[168],{"categories":2706},[137],{"categories":2708},[158],{"categories":2710},[116],{"categories":2712},[116],{"categories":2714},[116],{"categories":2716},[137],{"categories":2718},[116],{"categories":2720},[137],{"categories":2722},[119],{"categories":2724},[119],{"categories":2726},[168],{"categories":2728},[119],{"categories":2730},[116],{"categories":2732},[168],{"categories":2734},[158],{"categories":2736},[],{"categories":2738},[119],{"categories":2740},[],{"categories":2742},[],{"categories":2744},[],{"categories":2746},[113],{"categories":2748},[116],{"categories":2750},[119],{"categories":2752},[110],{"categories":2754},[119],{"categories":2756},[175],{"categories":2758},[],{"categories":2760},[119],{"categories":2762},[],{"categories":2764},[110],{"categories":2766},[119],{"categories":2768},[],{"categories":2770},[119],{"categories":2772},[116],{"categories":2774},[137],{"categories":2776},[116],{"categories":2778},[119],{"categories":2780},[137],{"categories":2782},[119],{"categories":2784},[168],{"categories":2786},[158],{"categories":2788},[110],{"categories":2790},[],{"categories":2792},[119],{"categories":2794},[158],{"categories":2796},[432],{"categories":2798},[137],{"categories":2800},[116],{"categories":2802},[158],{"categories":2804},[110],{"categories":2806},[],{"categories":2808},[119],{"categories":2810},[119],{"categories":2812},[116],{"categories":2814},[],{"categories":2816},[119],{"categories":2818},[122],{"categories":2820},[137],{"categories":2822},[119],{"categories":2824},[113],{"categories":2826},[],{"categories":2828},[116],{"categories":2830},[122],{"categories":2832},[116],{"categories":2834},[119],{"categories":2836},[137],{"categories":2838},[110],{"categories":2840},[432],{"categories":2842},[116],{"categories":2844},[116],{"categories":2846},[116],{"categories":2848},[137],{"categories":2850},[113],{"categories":2852},[116],{"categories":2854},[158],{"categories":2856},[137],{"categories":2858},[432],{"categories":2860},[116],{"categories":2862},[],{"categories":2864},[],{"categories":2866},[432],{"categories":2868},[161],{"categories":2870},[119],{"categories":2872},[119],{"categories":2874},[137],{"categories":2876},[116],{"categories":2878},[110],{"categories":2880},[158],{"categories":2882},[119],{"categories":2884},[116],{"categories":2886},[175],{"categories":2888},[116],{"categories":2890},[119],{"categories":2892},[],{"categories":2894},[116],{"categories":2896},[116],{"categories":2898},[137],{"categories":2900},[110],{"categories":2902},[],{"categories":2904},[116],{"categories":2906},[116],{"categories":2908},[168],{"categories":2910},[158],{"categories":2912},[116,119],{"categories":2914},[175,113],{"categories":2916},[116],{"categories":2918},[],{"categories":2920},[119],{"categories":2922},[],{"categories":2924},[168],{"categories":2926},[116],{"categories":2928},[137],{"categories":2930},[],{"categories":2932},[119],{"categories":2934},[],{"categories":2936},[158],{"categories":2938},[119],{"categories":2940},[110],{"categories":2942},[119],{"categories":2944},[116],{"categories":2946},[432],{"categories":2948},[175],{"categories":2950},[113],{"categories":2952},[113],{"categories":2954},[110],{"categories":2956},[110],{"categories":2958},[116],{"categories":2960},[119],{"categories":2962},[116],{"categories":2964},[116],{"categories":2966},[110],{"categories":2968},[116],{"categories":2970},[175],{"categories":2972},[137],{"categories":2974},[116],{"categories":2976},[119],{"categories":2978},[116],{"categories":2980},[],{"categories":2982},[168],{"categories":2984},[],{"categories":2986},[119],{"categories":2988},[110],{"categories":2990},[],{"categories":2992},[432],{"categories":2994},[116],{"categories":2996},[],{"categories":2998},[137],{"categories":3000},[119],{"categories":3002},[168],{"categories":3004},[116],{"categories":3006},[119],{"categories":3008},[168],{"categories":3010},[119],{"categories":3012},[137],{"categories":3014},[110],{"categories":3016},[137],{"categories":3018},[168],{"categories":3020},[116],{"categories":3022},[158],{"categories":3024},[116],{"categories":3026},[116],{"categories":3028},[116],{"categories":3030},[116],{"categories":3032},[119],{"categories":3034},[116],{"categories":3036},[119],{"categories":3038},[116],{"categories":3040},[110],{"categories":3042},[116],{"categories":3044},[119],{"categories":3046},[158],{"categories":3048},[110],{"categories":3050},[119],{"categories":3052},[158],{"categories":3054},[],{"categories":3056},[116],{"categories":3058},[116],{"categories":3060},[168],{"categories":3062},[],{"categories":3064},[119],{"categories":3066},[175],{"categories":3068},[116],{"categories":3070},[137],{"categories":3072},[175],{"categories":3074},[119],{"categories":3076},[113],{"categories":3078},[113],{"categories":3080},[116],{"categories":3082},[110],{"categories":3084},[],{"categories":3086},[116],{"categories":3088},[],{"categories":3090},[110],{"categories":3092},[116],{"categories":3094},[119],{"categories":3096},[119],{"categories":3098},[],{"categories":3100},[168],{"categories":3102},[168],{"categories":3104},[175],{"categories":3106},[158],{"categories":3108},[],{"categories":3110},[116],{"categories":3112},[110],{"categories":3114},[116],{"categories":3116},[168],{"categories":3118},[110],{"categories":3120},[137],{"categories":3122},[137],{"categories":3124},[],{"categories":3126},[137],{"categories":3128},[119],{"categories":3130},[158],{"categories":3132},[161],{"categories":3134},[116],{"categories":3136},[],{"categories":3138},[137],{"categories":3140},[168],{"categories":3142},[113],{"categories":3144},[116],{"categories":3146},[110],{"categories":3148},[432],{"categories":3150},[110],{"categories":3152},[],{"categories":3154},[],{"categories":3156},[137],{"categories":3158},[],{"categories":3160},[119],{"categories":3162},[119],{"categories":3164},[119],{"categories":3166},[],{"categories":3168},[116],{"categories":3170},[],{"categories":3172},[137],{"categories":3174},[110],{"categories":3176},[158],{"categories":3178},[116],{"categories":3180},[137],{"categories":3182},[137],{"categories":3184},[],{"categories":3186},[137],{"categories":3188},[110],{"categories":3190},[116],{"categories":3192},[],{"categories":3194},[119],{"categories":3196},[119],{"categories":3198},[110],{"categories":3200},[],{"categories":3202},[],{"categories":3204},[],{"categories":3206},[158],{"categories":3208},[119],{"categories":3210},[116],{"categories":3212},[],{"categories":3214},[],{"categories":3216},[],{"categories":3218},[158],{"categories":3220},[],{"categories":3222},[110],{"categories":3224},[],{"categories":3226},[],{"categories":3228},[158],{"categories":3230},[116],{"categories":3232},[137],{"categories":3234},[],{"categories":3236},[175],{"categories":3238},[137],{"categories":3240},[175],{"categories":3242},[116],{"categories":3244},[],{"categories":3246},[],{"categories":3248},[119],{"categories":3250},[],{"categories":3252},[],{"categories":3254},[119],{"categories":3256},[116],{"categories":3258},[],{"categories":3260},[119],{"categories":3262},[137],{"categories":3264},[175],{"categories":3266},[161],{"categories":3268},[119],{"categories":3270},[119],{"categories":3272},[],{"categories":3274},[],{"categories":3276},[],{"categories":3278},[137],{"categories":3280},[],{"categories":3282},[],{"categories":3284},[158],{"categories":3286},[110],{"categories":3288},[],{"categories":3290},[113],{"categories":3292},[175],{"categories":3294},[116],{"categories":3296},[168],{"categories":3298},[110],{"categories":3300},[161],{"categories":3302},[113],{"categories":3304},[168],{"categories":3306},[],{"categories":3308},[],{"categories":3310},[119],{"categories":3312},[110],{"categories":3314},[158],{"categories":3316},[110],{"categories":3318},[119],{"categories":3320},[432],{"categories":3322},[119],{"categories":3324},[],{"categories":3326},[116],{"categories":3328},[137],{"categories":3330},[168],{"categories":3332},[],{"categories":3334},[158],{"categories":3336},[137],{"categories":3338},[110],{"categories":3340},[119],{"categories":3342},[116],{"categories":3344},[113],{"categories":3346},[119,432],{"categories":3348},[119],{"categories":3350},[168],{"categories":3352},[116],{"categories":3354},[161],{"categories":3356},[175],{"categories":3358},[119],{"categories":3360},[],{"categories":3362},[119],{"categories":3364},[116],{"categories":3366},[113],{"categories":3368},[],{"categories":3370},[],{"categories":3372},[116],{"categories":3374},[161],{"categories":3376},[116],{"categories":3378},[],{"categories":3380},[137],{"categories":3382},[],{"categories":3384},[137],{"categories":3386},[168],{"categories":3388},[119],{"categories":3390},[116],{"categories":3392},[175],{"categories":3394},[168],{"categories":3396},[],{"categories":3398},[137],{"categories":3400},[116],{"categories":3402},[],{"categories":3404},[116],{"categories":3406},[119],{"categories":3408},[116],{"categories":3410},[119],{"categories":3412},[116],{"categories":3414},[116],{"categories":3416},[116],{"categories":3418},[116],{"categories":3420},[113],{"categories":3422},[],{"categories":3424},[122],{"categories":3426},[137],{"categories":3428},[116],{"categories":3430},[],{"categories":3432},[168],{"categories":3434},[116],{"categories":3436},[116],{"categories":3438},[119],{"categories":3440},[137],{"categories":3442},[116],{"categories":3444},[116],{"categories":3446},[113],{"categories":3448},[119],{"categories":3450},[158],{"categories":3452},[],{"categories":3454},[161],{"categories":3456},[116],{"categories":3458},[],{"categories":3460},[137],{"categories":3462},[175],{"categories":3464},[],{"categories":3466},[],{"categories":3468},[137],{"categories":3470},[137],{"categories":3472},[175],{"categories":3474},[110],{"categories":3476},[119],{"categories":3478},[119],{"categories":3480},[116],{"categories":3482},[113],{"categories":3484},[],{"categories":3486},[],{"categories":3488},[137],{"categories":3490},[161],{"categories":3492},[168],{"categories":3494},[119],{"categories":3496},[158],{"categories":3498},[161],{"categories":3500},[161],{"categories":3502},[],{"categories":3504},[137],{"categories":3506},[116],{"categories":3508},[116],{"categories":3510},[168],{"categories":3512},[],{"categories":3514},[137],{"categories":3516},[137],{"categories":3518},[137],{"categories":3520},[],{"categories":3522},[119],{"categories":3524},[116],{"categories":3526},[],{"categories":3528},[110],{"categories":3530},[113],{"categories":3532},[],{"categories":3534},[116],{"categories":3536},[116],{"categories":3538},[],{"categories":3540},[168],{"categories":3542},[],{"categories":3544},[],{"categories":3546},[],{"categories":3548},[],{"categories":3550},[116],{"categories":3552},[137],{"categories":3554},[],{"categories":3556},[],{"categories":3558},[116],{"categories":3560},[116],{"categories":3562},[116],{"categories":3564},[161],{"categories":3566},[116],{"categories":3568},[161],{"categories":3570},[],{"categories":3572},[161],{"categories":3574},[161],{"categories":3576},[432],{"categories":3578},[119],{"categories":3580},[168],{"categories":3582},[],{"categories":3584},[],{"categories":3586},[161],{"categories":3588},[168],{"categories":3590},[168],{"categories":3592},[168],{"categories":3594},[],{"categories":3596},[110],{"categories":3598},[168],{"categories":3600},[168],{"categories":3602},[110],{"categories":3604},[168],{"categories":3606},[113],{"categories":3608},[168],{"categories":3610},[168],{"categories":3612},[168],{"categories":3614},[161],{"categories":3616},[137],{"categories":3618},[137],{"categories":3620},[116],{"categories":3622},[168],{"categories":3624},[161],{"categories":3626},[432],{"categories":3628},[161],{"categories":3630},[161],{"categories":3632},[161],{"categories":3634},[],{"categories":3636},[113],{"categories":3638},[],{"categories":3640},[432],{"categories":3642},[168],{"categories":3644},[168],{"categories":3646},[168],{"categories":3648},[119],{"categories":3650},[137,113],{"categories":3652},[161],{"categories":3654},[],{"categories":3656},[],{"categories":3658},[161],{"categories":3660},[],{"categories":3662},[161],{"categories":3664},[137],{"categories":3666},[119],{"categories":3668},[],{"categories":3670},[168],{"categories":3672},[116],{"categories":3674},[158],{"categories":3676},[],{"categories":3678},[116],{"categories":3680},[],{"categories":3682},[137],{"categories":3684},[110],{"categories":3686},[161],{"categories":3688},[],{"categories":3690},[168],{"categories":3692},[137],[3694,3923,4075,4152],{"id":3695,"title":3696,"ai":3697,"body":3702,"categories":3881,"created_at":65,"date_modified":65,"description":3706,"extension":66,"faq":65,"featured":67,"kicker_label":65,"meta":3882,"navigation":86,"path":3907,"published_at":65,"question":65,"scraped_at":3908,"seo":3909,"sitemap":3910,"source_id":3911,"source_name":3912,"source_type":3913,"source_url":3914,"stem":3915,"tags":3916,"thumbnail_url":65,"tldr":3920,"tweet":65,"unknown_tags":3921,"__hash__":3922},"summaries\u002Fsummaries\u002F8ccff9c28a5e07d2-run-vibevoice-stt-locally-on-mac-in-one-uv-command-summary.md","Run VibeVoice STT Locally on Mac in One uv Command",{"provider":7,"model":8,"input_tokens":3698,"output_tokens":3699,"processing_time_ms":3700,"cost_usd":3701},5072,2597,26872,0.0022904,{"type":14,"value":3703,"toc":3876},[3704,3707,3711,3722,3731,3745,3831,3842,3846,3849,3862,3865,3869,3872],[22,3705,3706],{},"This link post demonstrates running Microsoft's VibeVoice, a Whisper-style speech-to-text model with built-in speaker diarization, locally on Apple Silicon. Released January 21, 2026, and MIT-licensed, it uses the 5.71GB 4-bit MLX-quantized version of the 17.3GB original for efficient inference.",[17,3708,3710],{"id":3709},"one-liner-command-delivers-full-transcription","One-Liner Command Delivers Full Transcription",[22,3712,3713,3714,3717,3718,3721],{},"Install and run via ",[29,3715,3716],{},"uv"," and ",[29,3719,3720],{},"mlx-audio",":",[3723,3724,3729],"pre",{"className":3725,"code":3727,"language":3728},[3726],"language-text","uv run --with mlx-audio mlx_audio.stt.generate \\\n  --model mlx-community\u002FVibeVoice-ASR-4bit \\\n  --audio lenny.mp3 --output-path lenny \\\n  --format json --verbose --max-tokens 32768\n","text",[29,3730,3727],{"__ignoreMap":58},[22,3732,3733,3734,3717,3737,3740,3741,3744],{},"This handles ",[29,3735,3736],{},".mp3",[29,3738,3739],{},".wav"," inputs. Default ",[29,3742,3743],{},"--max-tokens 8192"," covers ~25min audio; increase to 32768 for up to ~59min (model limit trims longer files). Outputs JSON array of segments like:",[3723,3746,3750],{"className":3747,"code":3748,"language":3749,"meta":58,"style":58},"language-json shiki shiki-themes github-light github-dark","{\n  \"text\": \"And an open question for me is...\",\n  \"start\": 13.85,\n  \"end\": 19.5,\n  \"duration\": 5.65,\n  \"speaker_id\": 0\n}\n","json",[29,3751,3752,3761,3777,3789,3801,3814,3825],{"__ignoreMap":58},[3753,3754,3757],"span",{"class":3755,"line":3756},"line",1,[3753,3758,3760],{"class":3759},"sVt8B","{\n",[3753,3762,3763,3767,3770,3774],{"class":3755,"line":59},[3753,3764,3766],{"class":3765},"sj4cs","  \"text\"",[3753,3768,3769],{"class":3759},": ",[3753,3771,3773],{"class":3772},"sZZnC","\"And an open question for me is...\"",[3753,3775,3776],{"class":3759},",\n",[3753,3778,3779,3782,3784,3787],{"class":3755,"line":82},[3753,3780,3781],{"class":3765},"  \"start\"",[3753,3783,3769],{"class":3759},[3753,3785,3786],{"class":3765},"13.85",[3753,3788,3776],{"class":3759},[3753,3790,3791,3794,3796,3799],{"class":3755,"line":83},[3753,3792,3793],{"class":3765},"  \"end\"",[3753,3795,3769],{"class":3759},[3753,3797,3798],{"class":3765},"19.5",[3753,3800,3776],{"class":3759},[3753,3802,3804,3807,3809,3812],{"class":3755,"line":3803},5,[3753,3805,3806],{"class":3765},"  \"duration\"",[3753,3808,3769],{"class":3759},[3753,3810,3811],{"class":3765},"5.65",[3753,3813,3776],{"class":3759},[3753,3815,3817,3820,3822],{"class":3755,"line":3816},6,[3753,3818,3819],{"class":3765},"  \"speaker_id\"",[3753,3821,3769],{"class":3759},[3753,3823,3824],{"class":3765},"0\n",[3753,3826,3828],{"class":3755,"line":3827},7,[3753,3829,3830],{"class":3759},"}\n",[22,3832,3833,3834,3837,3838,3841],{},"Load JSON into Datasette Lite (",[29,3835,3836],{},"https:\u002F\u002Flite.dssette.io\u002F?json=URL",") to facet by ",[29,3839,3840],{},"speaker_id"," and browse turns—accurately distinguishes speakers, even voice changes in intros.",[17,3843,3845],{"id":3844},"m5-max-performance-fast-for-local-use","M5 Max Performance: Fast for Local Use",[22,3847,3848],{},"On 128GB M5 Max MacBook Pro, 99.8min podcast (trimmed to 59min) took 524.79s total:",[3850,3851,3852,3856,3859],"ul",{},[3853,3854,3855],"li",{},"Prompt: 26,615 tokens at 50.718 t\u002Fs",[3853,3857,3858],{},"Generation: 20,248 tokens at 38.585 t\u002Fs",[3853,3860,3861],{},"Peak reported: 30.44GB RAM (Activity Monitor showed 61.5GB prefill, 18GB generation)",[22,3863,3864],{},"That's 8min 45s for ~1hr audio, enabling quick local prototyping without cloud costs.",[17,3866,3868],{"id":3867},"handling-long-audio-requires-splitting","Handling Long Audio Requires Splitting",[22,3870,3871],{},"Model caps at ~59min; for longer files, split with 1min overlaps to align speaker IDs and avoid cut-off words. Align segments post-processing to merge full transcripts.",[3873,3874,3875],"style",{},"html pre.shiki code .sVt8B, html code.shiki .sVt8B{--shiki-default:#24292E;--shiki-dark:#E1E4E8}html pre.shiki code .sj4cs, html code.shiki .sj4cs{--shiki-default:#005CC5;--shiki-dark:#79B8FF}html pre.shiki code .sZZnC, html code.shiki .sZZnC{--shiki-default:#032F62;--shiki-dark:#9ECBFF}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"title":58,"searchDepth":59,"depth":59,"links":3877},[3878,3879,3880],{"id":3709,"depth":59,"text":3710},{"id":3844,"depth":59,"text":3845},{"id":3867,"depth":59,"text":3868},[],{"content_references":3883,"triage":3904},[3884,3888,3891,3894,3897,3901],{"type":71,"title":3885,"url":3886,"context":3887},"microsoft\u002FVibeVoice","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FVibeVoice","mentioned",{"type":71,"title":3720,"author":3889,"url":3890,"context":73},"Prince Canuma","https:\u002F\u002Fgithub.com\u002FBlaizzy\u002Fmlx-audio",{"type":71,"title":3892,"url":3893,"context":3887},"mlx-community\u002FVibeVoice-ASR-4bit","https:\u002F\u002Fhuggingface.co\u002Fmlx-community\u002FVibeVoice-ASR-4bit",{"type":71,"title":3895,"url":3896,"context":3887},"microsoft\u002FVibeVoice-ASR","https:\u002F\u002Fhuggingface.co\u002Fmicrosoft\u002FVibeVoice-ASR\u002Ftree\u002Fmain",{"type":3898,"title":3899,"url":3900,"context":3887},"podcast","podcast appearance with Lenny Rachitsky","https:\u002F\u002Fsimonwillison.net\u002F2026\u002FApr\u002F2\u002Flennys-podcast\u002F",{"type":71,"title":3902,"url":3903,"context":73},"Datasette Lite","https:\u002F\u002Flite.datasette.io\u002F",{"relevance":3803,"novelty":83,"quality":83,"actionability":3803,"composite":3905,"reasoning":3906},4.55,"Category: AI & LLMs. The article provides a practical guide on running a specific AI model for speech-to-text transcription, addressing the needs of developers looking to implement AI features in their products. It includes a concrete command for execution and performance metrics, making it immediately actionable for the target audience.","\u002Fsummaries\u002F8ccff9c28a5e07d2-run-vibevoice-stt-locally-on-mac-in-one-uv-command-summary","2026-05-03 17:01:59",{"title":3696,"description":3706},{"loc":3907},"8ccff9c28a5e07d2","Simon Willison's Weblog","article","https:\u002F\u002Fsimonwillison.net\u002F2026\u002FApr\u002F27\u002Fvibevoice\u002F#atom-everything","summaries\u002F8ccff9c28a5e07d2-run-vibevoice-stt-locally-on-mac-in-one-uv-command-summary",[3917,3918,98,3919],"python","ai-tools","speech-to-text","Transcribe up to 59min audio with Microsoft's MIT-licensed VibeVoice model using mlx-audio: uv one-liner on M5 Max Mac processes 1hr podcast in 524s (8:45min) at 30-61GB RAM peak, outputs speaker-diarized JSON segments.",[98,3919],"Q9tnX8SIMUxa-_WyoFfW0YtnSs3O4mbyQR0Om301BMo",{"id":3924,"title":3925,"ai":3926,"body":3931,"categories":4052,"created_at":65,"date_modified":65,"description":58,"extension":66,"faq":65,"featured":67,"kicker_label":65,"meta":4053,"navigation":86,"path":4061,"published_at":4062,"question":65,"scraped_at":4062,"seo":4063,"sitemap":4064,"source_id":4065,"source_name":4066,"source_type":3913,"source_url":4067,"stem":4068,"tags":4069,"thumbnail_url":65,"tldr":4072,"tweet":65,"unknown_tags":4073,"__hash__":4074},"summaries\u002Fsummaries\u002F4a3442a5ca8c1935-custom-elevated-sandbox-enables-safe-codex-on-wind-summary.md","Custom Elevated Sandbox Enables Safe Codex on Windows",{"provider":7,"model":8,"input_tokens":3927,"output_tokens":3928,"processing_time_ms":3929,"cost_usd":3930},8671,1926,24099,0.00219035,{"type":14,"value":3932,"toc":4046},[3933,3937,3940,3944,3985,3989,4036,4040],[17,3934,3936],{"id":3935},"windows-isolation-shortfalls-demand-custom-sandbox","Windows Isolation Shortfalls Demand Custom Sandbox",[22,3938,3939],{},"Existing Windows tools fail for AI coding agents like Codex, which drive open-ended developer workflows (shells, Git, Python, builds). AppContainer suits scoped apps but not dynamic agent binaries. Windows Sandbox offers VM isolation but requires host\u002Fguest bridging and excludes Home SKUs, blocking direct workspace access. Mandatory Integrity Control (MIC) labels workspaces low-integrity, exposing them to all low-trust processes—not just Codex—risking broader compromise. Result: Codex defaults force users to approve every command (inefficient) or enable full access (unsafe). Solution: Build OS-enforced sandbox with file write limits to workspace (current directory + config.toml writable_roots), read access matching user, and no outbound network unless approved.",[17,3941,3943],{"id":3942},"unelevated-prototype-uses-sids-and-restricted-tokens-for-granular-writes","Unelevated Prototype Uses SIDs and Restricted Tokens for Granular Writes",[22,3945,3946,3947,3950,3951,3954,3955,3954,3958,3961,3962,3964,3965,3967,3968,3954,3971,3954,3974,3954,3977,3980,3981,3984],{},"First prototype avoids admin elevation by creating synthetic ",[29,3948,3949],{},"sandbox-write"," SID, granting it write\u002Fexecute\u002Fdelete on workspace and denying on ",[29,3952,3953],{},".git",", ",[29,3956,3957],{},".codex",[29,3959,3960],{},".agents",". Launches commands under write-restricted token requiring dual checks: normal user ACL + ",[29,3963,3949],{}," SID access (restricted list: Everyone, session SID, ",[29,3966,3949],{},"). This enforces writes only where intended without modifying host broadly. Network limits use advisory env vars: ",[29,3969,3970],{},"HTTPS_PROXY=http:\u002F\u002F127.0.0.1:9",[29,3972,3973],{},"ALL_PROXY=http:\u002F\u002F127.0.0.1:9",[29,3975,3976],{},"GIT_HTTPS_PROXY=http:\u002F\u002F127.0.0.1:9",[29,3978,3979],{},"GIT_SSH_COMMAND=cmd \u002Fc exit 1",", plus ",[29,3982,3983],{},"denybin"," PATH stubs for SSH\u002FSCP. Tradeoffs: Slow ACL setup on large dirs, hard to reconfigure, weak network (bypassable by custom sockets or non-proxy tools). Firewall infeasible unelevated—can't target restricted tokens or child processes like Git\u002FPython.",[17,3986,3988],{"id":3987},"elevated-redesign-leverages-dedicated-users-and-firewall-for-strong-isolation","Elevated Redesign Leverages Dedicated Users and Firewall for Strong Isolation",[22,3990,3991,3992,3995,3996,3999,4000,4003,4004,3954,4007,3954,4010,4013,4014,4017,4018,4021,4022,4025,4026,3954,4029,3954,4032,4035],{},"Shift to elevation at setup creates local users ",[29,3993,3994],{},"CodexSandboxOffline"," (firewall-blocked) and ",[29,3997,3998],{},"CodexSandboxOnline"," (network-allowed), with encrypted DPAPI credentials. Setup binary ",[29,4001,4002],{},"codex-windows-sandbox-setup.exe"," handles: synthetic SID, users, firewall rules blocking all outbound for Offline user, async read ACLs on dirs like ",[29,4005,4006],{},"C:\\Users\\\u003Cuser>",[29,4008,4009],{},"C:\\Windows",[29,4011,4012],{},"C:\\Program Files",". Command flow splits: ",[29,4015,4016],{},"codex.exe"," launches ",[29,4019,4020],{},"codex-command-runner.exe"," as sandbox user via ",[29,4023,4024],{},"CreateProcessWithLogonW","; runner creates restricted token (same SID list) on sandbox side using ",[29,4027,4028],{},"OpenProcessToken",[29,4030,4031],{},"CreateRestrictedToken",[29,4033,4034],{},"CreateProcessAsUserW"," for child. Ensures read equivalence to real user, write restrictions, and per-session firewall scoping without blocking all Python\u002FGit globally. Setup once, then frictionless: agents run tests, edit files, Git branch in workspace without net exfil or stray writes.",[17,4037,4039],{"id":4038},"safety-usability-balance-matches-macoslinux-sandboxes","Safety-Usability Balance Matches macOS\u002FLinux Sandboxes",[22,4041,4042,4043,4045],{},"Final multi-binary architecture (",[29,4044,4016],{},", setup.exe, runner.exe, child) mirrors macOS Seatbelt\u002F.sbpl and Linux seccomp\u002Fbubblewrap: OS primitives for process tree isolation. Complexity earned—each layer solves privilege walls, token boundaries, async costs—yielding production sandbox where agents act like developers (full reads, targeted writes) but can't escape bounds. Users avoid tedious approvals or risky full access, matching cross-platform delight.",{"title":58,"searchDepth":59,"depth":59,"links":4047},[4048,4049,4050,4051],{"id":3935,"depth":59,"text":3936},{"id":3942,"depth":59,"text":3943},{"id":3987,"depth":59,"text":3988},{"id":4038,"depth":59,"text":4039},[432],{"content_references":4054,"triage":4058},[4055],{"type":71,"title":4056,"url":4057,"context":3887},"Codex","https:\u002F\u002Fopenai.com\u002Fcodex\u002F",{"relevance":83,"novelty":82,"quality":83,"actionability":82,"composite":4059,"reasoning":4060},3.6,"Category: AI & LLMs. The article discusses a custom sandbox solution for Codex on Windows, addressing specific pain points related to security and usability for AI coding agents. It provides a detailed overview of the sandbox's architecture, which is relevant for developers looking to implement AI tools safely.","\u002Fsummaries\u002F4a3442a5ca8c1935-custom-elevated-sandbox-enables-safe-codex-on-wind-summary","2026-05-13 19:01:08",{"title":3925,"description":58},{"loc":4061},"4a3442a5ca8c1935","OpenAI News","https:\u002F\u002Fopenai.com\u002Findex\u002Fbuilding-codex-windows-sandbox","summaries\u002F4a3442a5ca8c1935-custom-elevated-sandbox-enables-safe-codex-on-wind-summary",[4070,4071,3918],"agents","devops","OpenAI built a custom Windows sandbox for Codex using dedicated users, restricted tokens, firewall rules, and multi-binary setup to limit writes to workspace, block outbound network by default, and grant user-like reads without constant approvals.",[],"12ruRo00cZWNKfq-h3jFzRmeUgZDzM6fv_6K8x5Hb6o",{"id":4076,"title":4077,"ai":4078,"body":4083,"categories":4121,"created_at":65,"date_modified":65,"description":58,"extension":66,"faq":65,"featured":67,"kicker_label":65,"meta":4122,"navigation":86,"path":4136,"published_at":4137,"question":65,"scraped_at":4138,"seo":4139,"sitemap":4140,"source_id":4141,"source_name":93,"source_type":94,"source_url":4142,"stem":4143,"tags":4144,"thumbnail_url":4147,"tldr":4148,"tweet":4149,"unknown_tags":4150,"__hash__":4151},"summaries\u002Fsummaries\u002F6c1e155d947b9d8e-agents-train-models-via-hugging-face-skills-summary.md","Agents Train Models via Hugging Face Skills",{"provider":7,"model":8,"input_tokens":4079,"output_tokens":4080,"processing_time_ms":4081,"cost_usd":4082},6822,1777,23400,0.00223025,{"type":14,"value":4084,"toc":4116},[4085,4089,4092,4095,4099,4106,4110,4113],[17,4086,4088],{"id":4087},"open-models-surpass-closed-with-full-customization","Open Models Surpass Closed with Full Customization",[22,4090,4091],{},"Open-weight models like GLM-4.1 now lead the Artificial Analysis Intelligence Index over closed models, with the gap closing per release. Full weight access enables quantization (e.g., GGUF 4-bit fits Gemma-2 large in 24GB L4 GPU VRAM), fine-tuning, and edge\u002Fbrowser deployment without data exfiltration—critical amid cloud performance drops and breaches. Hugging Face Hub (nearing 3M models) centralizes this: filter agentic models (VLMs for screenshot-based computer use or pure LLMs), compare via benchmark datasets (SWE-bench Pro for coding, AIME, humanities exams—GLM-4.1 tops SWE-bench), and route inference to fastest\u002Fcheapest providers (Groq, Cerebras) with tool-use visibility.",[22,4093,4094],{},"Traces repos store\u002Fexplore agent sessions (Cody, Cline, Pi)—upload paths, view parsed interactions in dataset viewer, retrain later. This cuts model selection friction from 3M options.",[17,4096,4098],{"id":4097},"local-coding-agents-run-seamlessly-on-open-models","Local Coding Agents Run Seamlessly on Open Models",[22,4100,4101,4102,4105],{},"Serve agents locally via llama.cpp server, LM Studio, or Ollama—Hub's 'Apps' tab lists compatible local tools; model cards show GGUF quants, hardware fits, and 2-3 line commands (e.g., ",[29,4103,4104],{},"ollama run \u003Chub-id>"," launches llama-agent binary). Favorites: Pi (simple setup, remote\u002Flocal), Hermes agents (superior memory, Slack\u002FWhatsApp integration—fixed speaker's own Slack bug autonomously). Pair with GLM-4.1; upcoming Gemma-2, Minimax rumored. Vibe-check via inference providers before local deploy.",[17,4107,4109],{"id":4108},"skills-turn-agents-into-ai-engineers","Skills Turn Agents into AI Engineers",[22,4111,4112],{},"Hugging Face Skills plug Hub into agents (Claude Code, Gemini): CLI skill manages repos\u002Fjobs\u002Fdemos; Dataset skill explores via viewer API; Gradio skill builds demos. Star: LLM Trainer skill fine-tunes LLMs\u002FVLMs\u002Fobject detectors (handles bounding boxes)—prompt \"train Qwen2-VL on LLaVA Instruct Mix,\" agent queries batch size\u002Fvalidation split, computes VRAM\u002Fjob cost, launches on HF infra (or local), outputs to Hub.",[22,4114,4115],{},"MCP server exposes models\u002Fdatasets\u002Fspaces\u002Fjobs\u002Fsemantic search—toggle 'dynamic spaces' for full app store querying (e.g., \"generate baklava of yarn\" calls Qwen2 image gen). Colleague's pipeline: agent picks top OCR-bench model (Chandram), writes\u002Fscripts job via skills, OCRs 30K papers on HF Jobs\u002FBuckets (cheaper S3), hosts without manual infra math. Outcome: agents handle end-to-end ML workflows—what took days of calculation is now a prompt.",{"title":58,"searchDepth":59,"depth":59,"links":4117},[4118,4119,4120],{"id":4087,"depth":59,"text":4088},{"id":4097,"depth":59,"text":4098},{"id":4108,"depth":59,"text":4109},[],{"content_references":4123,"triage":4133},[4124,4126,4129,4131],{"type":78,"title":4125,"context":3887},"Artificial Analysis Intelligence Index",{"type":4127,"title":4128,"context":3887},"dataset","SWE-bench Pro",{"type":4127,"title":4130,"context":3887},"AIME",{"type":4127,"title":4132,"context":3887},"OCR bench",{"relevance":3803,"novelty":83,"quality":83,"actionability":83,"composite":4134,"reasoning":4135},4.35,"Category: AI & LLMs. The article provides in-depth insights into using Hugging Face skills for fine-tuning models, addressing practical applications for AI-powered product builders. It details how agents can manage model training and deployment, which is directly actionable for developers looking to integrate AI into their products.","\u002Fsummaries\u002F6c1e155d947b9d8e-agents-train-models-via-hugging-face-skills-summary","2026-05-13 17:00:06","2026-05-13 19:00:18",{"title":4077,"description":58},{"loc":4136},"6c1e155d947b9d8e","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=OV56RddyFuU","summaries\u002F6c1e155d947b9d8e-agents-train-models-via-hugging-face-skills-summary",[4070,4145,3918,4146],"llm","open-source","https:\u002F\u002Fi.ytimg.com\u002Fvi\u002FOV56RddyFuU\u002Fhqdefault.jpg","Hugging Face skills let coding agents fine-tune VLMs like Qwen2VL on datasets like LLaVA Instruct Mix with one prompt: agents calculate VRAM, pick instances, and launch jobs remotely or locally.","Hugging Face engineer Merve Noyan demos HF Hub tools for agentic open-model workflows: benchmark filters (SWE-bench, AIME), inference provider routing (fastest\u002Fcheapest), traces repos for agent sessions, and skills like the LLM trainer that let agents fine-tune VLMs via prompts, including a live Claude Code example handling VRAM and job launch.",[],"34PjzePxXcXcfGg_SMNR1dcTLhbdN8zPHq3M5lg9fS8",{"id":4153,"title":4154,"ai":4155,"body":4160,"categories":4194,"created_at":65,"date_modified":65,"description":58,"extension":66,"faq":65,"featured":67,"kicker_label":65,"meta":4195,"navigation":86,"path":4215,"published_at":4216,"question":65,"scraped_at":4138,"seo":4217,"sitemap":4218,"source_id":4219,"source_name":93,"source_type":94,"source_url":4220,"stem":4221,"tags":4222,"thumbnail_url":4225,"tldr":4226,"tweet":4227,"unknown_tags":4228,"__hash__":4229},"summaries\u002Fsummaries\u002Fc87f3077967b2f97-chess-coach-pipeline-engines-detectors-llm-transla-summary.md","Chess Coach Pipeline: Engines + Detectors + LLM Translator",{"provider":7,"model":8,"input_tokens":4156,"output_tokens":4157,"processing_time_ms":4158,"cost_usd":4159},7106,1735,19878,0.0022662,{"type":14,"value":4161,"toc":4189},[4162,4166,4169,4172,4176,4179,4183,4186],[17,4163,4165],{"id":4164},"separate-evaluation-detection-and-translation-to-ground-llm-outputs","Separate Evaluation, Detection, and Translation to Ground LLM Outputs",[22,4167,4168],{},"LLMs hallucinate in chess because they predict tokens from language data, not calculate positions accurately—they falter after openings, as seen in Kaggle's LLM chess tournament where models like GPT lost badly. Bridge this with a pipeline: Run Stockfish (top classical engine) across the full game for best-move evaluations and lines. Extract structured context via detectors for tactics (forks, pins, skewers) and positional themes (doubled pawns, structural weaknesses). Add Maya (University of Toronto neural engine) for human-like move probabilities by rating (e.g., 1500 Elo), revealing if a Stockfish-optimal move is hard to spot (low probability). Feed this JSON to an LLM solely as translator, preventing reasoning errors. Result: Nuanced commentary like \"F5 threatens to trap your queen (Bg5 line), but capture the pawn to defend and escape,\" explaining threats, defenses, and plans beyond \"bad move.\"",[22,4170,4171],{},"This grounds explanations in facts, enabling brilliant-move detection (e.g., knight sac to checkmate) with why-it-works details, plus game-phase accuracy, ratings, and opening depth insights for coaching.",[17,4173,4175],{"id":4174},"close-feedback-loops-with-autonomous-agents-for-rapid-iteration","Close Feedback Loops with Autonomous Agents for Rapid Iteration",[22,4177,4178],{},"User flags bad commentary in-app, posting position, PGN, and output to Slack while injecting into a running Claude Code session via Channels (Anthropic's research-preview MCP for event injection, like OpenClaw). Claude invokes a custom \"commentary triage skill\": Analyzes position with Stockfish\u002Fdetectors, modifies prompts or adds detectors (e.g., new tactic), regenerates commentary, self-verifies, and queries Slack (\"What specifically feels wrong?\"). Operator approves from phone, triggering PR merge. Live demo showed Claude dismissing a false flag (\"nothing wrong\") autonomously. Humans-in-loop but mobile-scale; prunes massive initial JSON context iteratively for quality gains.",[17,4180,4182],{"id":4181},"balance-sub-3s-latency-and-quality-via-model-evals-and-trade-offs","Balance Sub-3s Latency and Quality via Model Evals and Trade-offs",[22,4184,4185],{},"Consumer apps demand instant post-game reviews (cycle moves one-by-one), so target sub-3s end-to-end: Gemini 1.5 Flash delivers ~1s time-to-first-token, ~3s average total. Avoid reasoning models' unpredictable delays (no spinning \"coach thinking\" screens). Quality via 16 thematic evals (tactics, blunders, anti-hallucination) from real games: LLM-as-judge on OpenRouter for quick model swaps (Gemini Flash: 75% pass; Claude thinking: 60% but slower; GPT-4o mini: lower accuracy, moderate latency). Human experts (speakers, strong players) final-check against manual calculation. Future: Deeper chat-coach tolerates latency for reasoning models.",[22,4187,4188],{},"Key learnings: Isolate data pipelines (Stockfish\u002Fdetectors) from LLM generation for speed\u002Freliability; build clear context extractors (start big, prune); leverage domain-expert evals\u002Fpartners; agent loops enable bus-to-PR iteration.",{"title":58,"searchDepth":59,"depth":59,"links":4190},[4191,4192,4193],{"id":4164,"depth":59,"text":4165},{"id":4174,"depth":59,"text":4175},{"id":4181,"depth":59,"text":4182},[],{"content_references":4196,"triage":4213},[4197,4201,4203,4206,4209,4211],{"type":4198,"title":4199,"author":4200,"context":80},"paper","Programming a Computer to Play Chess","Claude Shannon",{"type":71,"title":4202,"context":3887},"Stockfish",{"type":71,"title":4204,"author":4205,"context":3887},"Maya","University of Toronto",{"type":4207,"title":4208,"context":3887},"event","Deep Blue vs Kasparov",{"type":78,"title":4210,"context":3887},"Kaggle Game Arena LLM Chess Tournament",{"type":71,"title":4212,"context":3887},"Channels (Claude Code MCP)",{"relevance":3803,"novelty":83,"quality":83,"actionability":83,"composite":4134,"reasoning":4214},"Category: AI & LLMs. The article provides a detailed pipeline for improving LLM performance in chess coaching, addressing the specific pain point of hallucinations in LLMs by integrating classical engines and detectors. It offers actionable insights on how to implement this system, making it relevant and practical for developers looking to enhance AI applications.","\u002Fsummaries\u002Fc87f3077967b2f97-chess-coach-pipeline-engines-detectors-llm-transla-summary","2026-05-13 15:00:06",{"title":4154,"description":58},{"loc":4215},"c87f3077967b2f97","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=FlzpEGHNVKQ","summaries\u002Fc87f3077967b2f97-chess-coach-pipeline-engines-detectors-llm-transla-summary",[4145,4070,4223,4224],"prompt-engineering","ai-automation","https:\u002F\u002Fi.ytimg.com\u002Fvi\u002FFlzpEGHNVKQ\u002Fhqdefault.jpg","LLMs fail at chess due to hallucinations; fix by using Stockfish for evaluation, tactical\u002Fpositional detectors for concepts, and LLM only to translate into natural language—achieving sub-3s latency without errors.","Talk by Take Take Take engineers [Anant Dole](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fanantdole\u002F) and [Asbjørn Steinskog](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fasbj%C3%B8rn-ottesen-steinskog-a8000241\u002F) on their chess app's production game-review pipeline: Stockfish evals positions, detectors flag tactics like pins\u002Fforks, LLM translates to natural explanations at sub-3s latency. They live-demo a user-feedback loop piping bad comments to Claude Code via Channels for autonomous prompt\u002Fdetector tweaks and PRs.",[4224],"8lszXmxZyW7tbji7dhLGVVL6er8NS6Bp5eeHTzvg5UM"]