Coding with AI
bluemat briefs and decodes on Coding with AI.
- 'You don't need long context': what the compaction paper means for coding agents
- HarnessRouter pitches Harness Arena for comparing agent harness and model combinations
- Claude's Messages API adds message threads to cut resent history in agent loops
- Claude Code mods: in-session JavaScript hooks for guards, readouts and review views
- How Uber's AutoClean agents safely delete stale feature-flag code
- Meta puts LLM-generated bug-catching tests into production
- A ten-person game studio describes running its codebase with a fleet of agents
- Vercel CI enters beta, running only the Turborepo tasks a push affects
- Copilot Automations can now learn from outcomes and propose their own prompt changes
- Decoding Zalando's risk-based PR auto-approval and LiteLLM proxy setup
- Cognition's FrontierCode 2.0 grades coding agents on whether maintainers would merge
- Entire launches a Git forge that scores every push with review agents
- A proposed protocol for measuring the human review time behind agent output
- Cursor agents can now click and type in desktop apps on your own machine
- Anthropic moves its monorepo off git to Scion as merges top 30,000 a day
- Subagents vs. skills: stop using subagents to hold instructions
- Google's agent-eval playbook: replacing vibe checks with trace-based regression gates
- Claude Code mods: programmable guardrails inside the agent harness
- Claude API version 2026-10-21 removes temperature, top_p and top_k
- OpenAI ships an official CLI for calling its API from the shell
- Ramp says agents wrote all the code for Laminar, its in-house agent harness
- Vercel's durable-harness: crash-resume for Claude Code, Codex, Pi and OpenCode
- OpenClaw's agent loop moved its web UI from Lit to Solid 2.0 in about two weeks
- How the Claude Code team reviews agent-written code, and what you can copy
- Agentic verification: give your coding agent checks it can run itself
- How Anthropic's Claude Code team reviews agent-written code, and what to copy
- Behavioral harnesses made a cheap coding model reliable, and a frontier one pricier
- How GitHub ported Copilot's runtime to Rust with agents and kept shipping
- OpenCode 2.0 turns the open-source coding agent into a scriptable background service
- Agent teams on Vibe Code Bench: 1.8–5.1x the cost, one significant score gain
- Anthropic publishes a playbook for running the SDLC around coding agents
- Agent Standup shows which Claude Code sub-agents are blocked, stuck or costly
- Simon Willison ships a Django blog feature by voice with Codex in ChatGPT desktop
- Google's FlowAgent paper reports deployment numbers for agentic test-failure fixes in CI
- MAI-Code-1.1-Flash gets a local build for Copilot, with a 120GB+ RAM recommendation
- AutoRubric: a Python library for rubric-based LLM judges, with a cheap Jev first pass
- Devin adds cross-session Memory and a daily Dreaming cleanup pass
- Decoding Uber's AI software factory: what a five-person team should copy
- SelfSearch: a coding agent rewrites its own harness, claims Codex parity for $4.03
- Birgitta Böckeler tests local models for agentic coding on Apple Silicon
- Filestage reports 50% more merged PRs with AI agents, credits CI guardrails
- Domenic Denicola's agentic coding setup: no-approval agents in a disposable Linux VM
- Bain says code review is absorbing the AI coding speedup
- Claude Code mods: in-session hooks that can rewrite tool calls and draw UI
- Qodo 3.0 previews PR Triage to review multi-repo agent output as one package
- Anthropic's measure-first agent loop: 3,000+ merges and a 3x faster claude.ai
- Keep acceptance tests out of your coding agent's reach, AgentField argues
- Claude Code's build-eval and hillclimb: eval design with a held-out check
bluemat home