№ 02 / SUMMARIES

#python

Every summary, chronological. Filter by category, tag, or source from the rail.

Tag · #python
DAY 01Yesterday MAY 12 · 20262 SUMMARIES
MarkTechPostAI & LLMs

Modular Hybrid-Memory Agent with OpenAI Tools

Build a production-ready autonomous agent in Python using hybrid vector+BM25 memory fused by RRF (K=60), modular tool dispatch, and a self-managing loop limited to 8 tool rounds for reliable reasoning and action.

MarkTechPost
MarkTechPostData Science & Visualization

skfolio: Build & Tune Portfolio Optimizers in Python

skfolio's scikit-learn API lets you construct, validate, and compare 18+ portfolio strategies—from baselines to HRP, Black-Litterman, factors, and tuned models—on S&P 500 returns with walk-forward CV and GridSearchCV.

DAY 02Monday MAY 11 · 20261 SUMMARIES
MarkTechPost

Memori: Persistent Memory for Multi-User LLM Agents

Register OpenAI clients with Memori to automatically store/retrieve scoped memories by user entity, agent process, and session, enabling context-aware agents across turns, users, and interactions without manual prompt management.

MarkTechPost
DAY 03Sunday MAY 10 · 20263 SUMMARIES
MarkTechPost

NadirClaw: Local Embeddings Route Prompts to Cheaper LLMs

Classify prompts as simple/complex using cosine similarity to precomputed centroids from all-MiniLM-L6-v2 embeddings—no API calls needed—then proxy OpenAI requests to Gemini Flash (cheap) or Pro (strong), saving ~70% on mixed workloads vs always-Pro.

MarkTechPost
Python in Plain EnglishSoftware Engineering

Pytest Fixtures: DRY Up Test Setup Code

Pytest fixtures eliminate repeated setup/teardown in tests by centralizing data prep, DB connections, and cleanup—use params for variations, scopes for reuse, and yield for teardown to scale suites without fragility.

Towards AIData Science & Visualization

Reproduce 2011 Sentiment Word Vectors in Python

Build sentiment-aware word embeddings from IMDb reviews via semantic learning with star ratings and linear SVM classification, reproducing Maas et al. (2011) – simple method rivals modern LLMs.

DAY 04Saturday MAY 9 · 20262 SUMMARIES
Towards AIAI & LLMs

Semantic Caching Cuts AI Agent Latency 91% via Intent Matching

Enterprise AI agents see 30-40% duplicate intents; semantic caching uses embeddings and cosine similarity (threshold 0.75) with LangGraph/Redis to serve cached responses, slashing LLM calls, costs, and latency by 91% on hits.

Towards AI
Towards AI

Hierarchical CrewAI Managers Coordinate Banking Agent Teams

Replace sequential agent chains with hierarchical workflows where a manager agent delegates to specialists, enabling parallel processing and adaptation for complex banking tasks like customer service (5 agents) and credit risk assessment (4 agents), while mixing LLMs optimizes costs.

DAY 05Friday MAY 8 · 20264 SUMMARIES
MarkTechPostData Science & Visualization

Scanpy Pipeline for PBMC scRNA-seq Clustering & Trajectories

Process PBMC-3k data with Scanpy: filter cells (min 200 genes, <2500 genes, <5% mt), remove Scrublet doublets, select HVGs (min_mean=0.0125, max_mean=3, min_disp=0.5), Leiden cluster at res=0.5, annotate via markers, infer PAGA/DPT trajectories, score IFN response.

MarkTechPost
Level Up CodingAI & LLMs

Collaborative AI Writer: WebSockets + CRDT + Claude

Build multi-user real-time AI writing with FastAPI WebSockets for connections, CRDTs for conflict-free text sync, Claude streaming fanned to all users, and per-user token-bucket rate limiting to avoid bursts.

Level Up CodingSoftware Engineering

Skip Heavy Clean Architecture in Python Unless Scale Demands It

Over-applying clean architecture in Python FastAPI apps requires 7 changes for one field addition, killing velocity; Django's simple models need just 2 lines, proving less structure ships faster.

MarkTechPostAI Automation

Stealth CloakBrowser Automation in Colab with Persistence

Run Playwright-style stealth Chromium automation in Google Colab by isolating sync APIs in a worker thread; customize contexts with viewport=1365x768, persist localStorage via storage_state.json or profile dirs, and inspect undetectable signals like webdriver=false.

DAY 06Thursday MAY 7 · 20266 SUMMARIES
UX CollectiveDesign & Frontend

Data-Centric Design Rules for Complex Apps

Center interaction design on data landscapes: learn Python and users' jobs, let data structure UIs, strip chrome, design empty states, and bridge mental/data models to align interfaces with real-world tasks.

UX Collective
AI Engineer

Optimize Live Agents: GEPA Prompts + Managed Vars

Tune production agents without redeploys using Logfire's managed variables for prompts/models and GEPA's genetic algorithm to evolve better prompts from evals on golden datasets.

Sam WitteveenAI & LLMs

IBM Granite Speech 4.1: 3 ASR Models for Accuracy, Features, Speed

IBM's 2B Granite Speech 4.1 suite offers three trade-offs: base leads Open ASR Leaderboard (WER 5.33, RTF 231), Plus adds diarization/timestamps, NAR hits RTF 1820 on H100 via transcript editing.

Generative AIAI Automation

Python Rules Turn Financial Signals into Thesis Verdicts

Classify stock theses into 10 claim types, map price/fundamentals signals to support/against/missing evidence using thresholds like drawdown >-15% or P/E<20, then assign verdicts like 'supported' based on evidence counts and gaps for a research copilot.

Generative AI

Build Thesis-Testing Copilot with MCP & Python

Parse natural-language investment theses into structured requests, fetch prices/fundamentals via EODHD MCP, compute market/business signals to generate evidence-based research memos with verdicts.

Python in Plain EnglishSoftware Engineering

Fire-and-Forget Background Tasks: Python's 500ms Rule

Keep request-response under 500ms by decoupling acknowledgment (HTTP 202) from execution. Use reference registries for asyncio, FastAPI BackgroundTasks for light work, multiprocessing for CPU tasks, or Celery for persistent, scalable jobs.

DAY 07May 6, 2026 MAY 6 · 20262 SUMMARIES
MarkTechPostAI & LLMs

Groq-Powered Research Agent with LangGraph Sub-Agents

Build a fast agentic research assistant using Groq's free Llama-3.3-70b API, LangGraph for loops, sandboxed tools for search/files/code/memory, modular skills, and sub-agents for delegation—demo researches SLMs and persists facts.

MarkTechPost
MarkTechPostSoftware Engineering

Build Reactive Multi-Page Web Apps with NiceGUI in Python

NiceGUI lets you create full web apps with shared state, routing, real-time charts, CRUD todos, validated forms, file uploads, and async chat using pure Python—no JS or HTML needed.

DAY 08May 5, 2026 MAY 5 · 20268 SUMMARIES
MarkTechPostAI & LLMs

Modular LLM Agent: Skills, Registry, Dynamic Routing

Build a Python agent system where LLMs dynamically select and chain modular skills via a central registry, enabling composable workflows, hot-loading, and multi-step reasoning.

MarkTechPost
Towards AIAI Automation

Compliant LLM Clinical Pipelines: 85% Skip LLMs

Use constrained decoding, lossy Pydantic parsing, deterministic Python computation/validation, and conditional LLM judging to build ALCOA++/21 CFR Part 11-compliant pipelines processing clinical data at $0.15 per 1K records, with 85% records avoiding LLMs entirely.

Python in Plain EnglishDevOps & Cloud

Replace Cron with Temporal for Reliable Data Jobs

Cron fails on retries, overlaps, and writes due to zero observability. Temporal workflows add retries (3s initial, 2x backoff, 8 max attempts), atomic writes, unique output files per run ID, SKIP overlap policy, and full execution history via UI—surviving crashes with state in Temporal.

Data and BeyondSoftware Engineering

Python Variables: Sticky Notes on Shared Objects

Forget 'pass-by-reference'—Python variables are labels binding to objects via 'call by sharing'. Mutable defaults like [] create shared state across calls, causing ghost bugs; fix by using None and instantiating inside functions.

MarkTechPostData Science & Visualization

Momentum Dampens GD Zigzags via Gradient Averaging

On anisotropic loss surfaces (condition number 100), vanilla GD zigzags and takes 185 steps to converge (loss <0.001); momentum with β=0.9 converges in 159 steps by canceling steep-direction oscillations while accelerating flat directions—but β=0.99 diverges.

Generative AIAI & LLMs

Local AI Agent Stack: Ollama as LLM, MCP as Libraries

Build a fully local agentic system treating LLMs as programming languages, MCP servers as libraries, and Markdown skills as programs—orchestrated via Python and JSON config for offline ops queries.

Towards AIAI & LLMs

Databricks RAG: Low-Dim Qwen3 + Rerank for 89% Recall@10

Minimize embedding dims to 256 with Qwen3 MRL (self-managed path), set num_results=50, always rerank ANN top-50 candidates for +15pts recall@10 over 74% baseline.

Towards AIAI & LLMs

Persist RAG Memory Across Turns with Lakebase PostgresSaver

Swap LangChain's InMemorySaver for PostgresSaver backed by Databricks Lakebase to maintain conversation history in RAG agents, enabling context-aware multi-turn responses like resolving 'it' to prior mentions across Model Serving requests.

DAY 09May 4, 2026 MAY 4 · 20262 SUMMARIES
MarkTechPostData Science & Visualization

Production ML Pipelines with ZenML: Custom Materializers & HPO

ZenML enables end-to-end ML pipelines with custom DatasetBundle materializers for metadata-rich serialization, fan-out over 4 hyperparameter configs for RandomForest/GradientBoosting/LogisticRegression, fan-in best-model selection by ROC AUC, full artifact tracking, and cache-driven reproducibility on breast cancer dataset.

MarkTechPost
AI EngineerAI & LLMs

Train GPT-2 LLM from Scratch on Laptop

Hands-on workshop: Build tokenizer, causal transformer, training loop in PyTorch to train tiny GPT-2 on Shakespeare locally (16GB RAM) or Colab – reveals core engineering without cloud.

Showing 30 of 166