ZeroNoise Logo zeronoise

Coding Agents Alpha Tracker

Live Daily at 8:00 AM Agent time: 8:00 AM GMT+00:00 – Europe / London

by avergin 111 sources

How top engineers use coding agents: workflows, techniques, tools, models and projects.

•
5 min read
• 74 docs
Theo's Council skill brings models from different families in to review changes and won't stop until they give a set score. Also: Steve Yegge's case for slowing down, Kent C. Dodds' software-factory tips and remote agent setup, and a larger context window for Gemini models in Antigravity.
•
5 min read
• 49 docs
Practitioners agree on routing between Opus 5.5 and Fable 5.2 by cost and difficulty. Riley Brown shows how giving an agent a cloud-compute skill changes what it tries, and LangChain argues agent goals should be scoped around the review loop.
•
5 min read
• 93 docs
Cursor's incident report shows how credentials left in coding-agent traces became a supply-chain attack. Also: ThePrimeagen and Antigravity put agent control flow into explicit code, Theo finds Gemini 4 Carbon 5x slower in real work, and Anthropic and LangChain release agent platforms.
•
5 min read
• 157 docs
Practitioners at AIE Code explained how they make agent output trustworthy, and Theo gave a working rule for choosing between Opus 5.5 and Fable 5.2. Gemini 4 Hydrogen launched as Google's fast, cheaper model, and early reports on it are mixed.
•
6 min read
• 139 docs
Geoffrey Huntley explains how he uses Nix to make agents safe and dependable. Theo reports on Gemini 4 Carbon in real use: slow, prone to making things up, but useful for security fixes. Anthropic has updated its Fable 5.2 ownership prompt.
•
5 min read
• 182 docs
Google's Gemini 4 Carbon is now generally available, with a multi-agent /swarm command in Antigravity. Theo's Fable 5.2 deep dive adds practical guidance on models and effort levels, and Geoffrey Huntley argues teams should invest in engineering basics rather than skill packs.
•
5 min read
• 218 docs
Anthropic's Fable 5.2 launch dominated the period. Practitioners shared pricing math, effort-level guidance, an ownership prompt, and when to pick it over Opus 5.5. Also covered: Simon Willison's live-iteration build, the Pi team's issue-triage bot, and new remote-machine controls for agents.
•
6 min read
• 119 docs
Two practitioner guides agree on the main point this period: agents improve when they have fast, definitive checks to run against their own work. Also covered: Simon Willison's pattern for long AI-written PR descriptions, Theo's warning about agent-built MCP auth, how Monaco structures agent work, and a counterpoint on MaxxBench.
•
5 min read
• 103 docs
Theo traces a reported shift in Opus 5.5's reasoning to an Anthropic summarizer rollout rather than lost capability. MaxxBench finds that models with similar DeepSWE scores split apart when tasks change slightly. Also: running Claude Code remotely through Claude Duet, a local-first T3 Code fork, and quick builds by Orosz and Karpathy.
•
6 min read
• 220 docs
Theo walks through how the Claude Code team gets agents to verify their work and limits automated review rounds. Also: Armin Ronacher's small agent "factory", T3 Code data showing Opus 5.5 on max reasoning fails more often than on high, and prompt and config tips.