#coding
Every summary, chronological. Filter by category, tag, or source from the rail.
Practical Loop Engineering for AI Agents
Loop engineering uses autonomous feedback cycles to automate repetitive tasks. By combining 'goal' primitives for bounded tasks and 'loop' primitives for scheduling, developers can build reliable agentic workflows while maintaining human oversight for critical judgment.
WebGrader: Self-Evolving Programmatic Evaluation for Web LLMs
WebGrader improves LLM web development capabilities by using a self-evolving programmatic grading system that automatically generates and refines test cases to ensure code accuracy.
Anthropic Enables Auto Mode by Default in Claude Code
Starting August 14, Anthropic will make 'auto mode' the default for Claude Code, citing higher safety efficacy compared to manual human review.
Agentic Engineering Patterns from the Claude Certified Architect Exam
Build robust AI agents by treating them as specialized, isolated units, managing context strictly, and designing loops that handle stop reasons rather than assuming successful execution.
AI EngineerSecure AI Coding: A Framework for Production-Ready Agents
To use AI agents securely, treat them like junior developers: enforce small, test-driven batches, provide scoped context, use hardened sandboxing, and verify output with traditional security tooling.
Google Cloud TechAgentic Engineering: From Writing Code to Orchestrating Systems
Agentic engineering shifts the developer's role from writing deterministic code to designing, constraining, and supervising autonomous AI systems that operate on probabilistic judgment.
IBM TechnologyAutomating Ascend C Operator Generation with AgenticCANN
AgenticCANN leverages a knowledge-augmented agentic evolution framework to automate the complex, manual process of writing high-performance Ascend C operators for AI hardware.
Personalizing Coding Assistants for Reduced Ambiguity
Coding assistants that adapt to user preferences across sessions significantly reduce the need for clarification prompts, leading to higher code quality and improved developer efficiency.
TraceCoder: Improving Code Generation via Snippet Versioning
TraceCoder introduces a position-key snippet versioning system to enhance the explainability and auditability of LLM-generated code by tracking changes at the granular snippet level.
Building AI-Powered Products: Workflows, Agents, and Community
A deep dive into modern design engineering, exploring how AI agents and mixed-media workflows are enabling builders to experiment faster, ship code directly, and foster community through interactive, live-demo projects.
Dive ClubKernel Forge: Automating CUDA Kernel Optimization with AI Agents
Kernel Forge is an agentic framework that automates the generation, compilation, and iterative optimization of CUDA kernels, bridging the gap between high-level LLM code generation and low-level hardware performance.
Shifting from Writing Code to Reviewing AI Output
AI coding agents don't replace developer craft; they shift the primary responsibility from writing code to rigorous review, verification, and production safety.
Google Cloud TechModernizing Scientific Software with Coding Agents
Coding agents accelerate scientific software development by automating tedious implementation tasks, allowing researchers to shift their focus from writing code to defining requirements, validating scientific accuracy, and ensuring long-term stewardship.
Execution-Grounded Security Testing for Coding Agents
Coding agents often introduce security vulnerabilities that static analysis misses. This paper proposes an execution-grounded testing framework that validates agent-generated code in sandboxed environments to detect runtime security flaws.
Optimizing AI-Driven Development with Claude Code
Leverage Claude Code on Google Cloud for intent-driven development by using voice interaction, iterative prompting, and CLI-based automation to build and verify complex applications.
Google Cloud TechBuilding Complex Apps with Claude Code and Dynamic Workflows
Claude Code's new dynamic workflows allow developers to automate complex, multi-step coding tasks by generating deterministic, parallelized JavaScript execution plans that can be saved, edited, and reused.
The Reality of Vibe Coding and Developer Identity
Vibe coding—using AI to build without deep knowledge of underlying syntax—is shifting developer identity from 'code author' to 'code reviewer' and 'agent orchestrator,' raising questions about the future of junior roles and technical skill retention.
Google Cloud TechHow AI is Reshaping the Integrated Development Environment
AI-powered IDEs are shifting from simple text editors to context-aware partners that automate refactoring, debugging, and code generation by analyzing entire codebases rather than individual files.
DeepSWE: A Contamination-Resistant Coding Benchmark
DeepSWE is a long-horizon coding benchmark using 113 original, human-authored tasks to prevent model contamination and reward hacking, providing a more accurate assessment of frontier model capabilities.
AI EngineerScaling Synthetic Data and Pre-training at Poolside
Poolside shares their methodology for scaling agentic coding models, emphasizing modular synthetic data pipelines, rigorous training-time verification, and the reality of silent hardware and numerical failures at scale.
Applying Control Theory to AI Coding Agents
Instead of using AI agents to generate massive, unreviewable pull requests, use control theory to build iterative loops that make small, verifiable, and incremental code changes.
AI EngineerThe Rise of the AI-Powered Designer and the End of the 'Dumb Device' Era
The hosts explore how AI is redefining the 'web designer' role, the shift from data-driven to intuition-led product building, and the rapid evolution of AI-integrated hardware and software.
Dive ClubImagination Engineering: Building with AI Agents
As AI models become capable of one-shotting technical execution, the primary bottleneck for builders shifts from coding to the ability to conceive bold, innovative ideas.
AI EngineerAndrej Karpathy's Engineering Philosophy
Andrej Karpathy's blog archives demonstrate a consistent engineering philosophy: demystifying complex systems through 'from-scratch' implementations, rigorous data-driven analysis, and practical, hands-on experimentation.
Meng To: Building Software with AI and Codex
Designer Meng To explains how he has transitioned to a 0% manual coding workflow by using Codex, local AI agents, and iterative prompting to build complex software products in days rather than months.
Dive ClubOrnith-1.0: Coding Models That Learn Their Own Harness
Ornith-1.0 achieves state-of-the-art performance for its size by incorporating the coding harness into the model's training gradient, allowing the model to dynamically generate its own execution scaffolds rather than relying on static, human-written ones.
Building Custom Apps with Claude Code: A Step-by-Step Guide
Learn a structured, iterative workflow to build custom software using Claude Code by focusing on upfront PRD shaping, milestone-based development, and agentic self-verification.
Optimizing Software Delivery with AI-Assisted Code Reviews
AI code review accelerates development and improves consistency by automating pattern detection, but it requires human oversight to manage context, architectural decisions, and false positives.
Writing JIT-Ready Python for CPython 3.14
Modern Python performance relies on writing predictable, type-consistent code that the Specializing Adaptive Interpreter can optimize, rather than relying on external JIT libraries like Numba.
Refactoring Pandas Workflows with .pipe()
The .pipe() method in Pandas enables cleaner, more readable ETL pipelines by chaining custom functions, reducing boilerplate code and improving maintainability compared to nested or sequential assignments.
Showing 30 of 277