Building Effective AI Agents(anthropic.com)
484 points by Anon84 | 84 comments
Anthropic engineering post from Dec 2024 on building LLM agents, arguing for simple, composable patterns over complex frameworks.
First screen, captured .
Looks similar
A postmortem of three recent issues(anthropic.com)
361 points by moatmoat | 112 comments
Anthropic engineering blog post giving a technical postmortem of three bugs that intermittently degraded Claude's responses, and what is changing.
Claude Advanced Tool Use(anthropic.com)
644 points by lebovic | 255 comments
Anthropic engineering blog post introducing three beta features on the Claude Developer Platform that let Claude discover, learn, and execute tools dynamically.
An update on recent Claude Code quality reports(anthropic.com)
905 points by mfiguiere | 673 comments
Anthropic engineering post explaining how recent Claude Code quality complaints traced to three separate changes, and what the company is changing in response.
We tasked Opus 4.6 using agent teams to build a C Compiler(anthropic.com)
690 points by modeless | 664 comments
Anthropic engineering blog post describing how teams of parallel Claude Opus 4.6 agents built a C compiler with minimal human involvement.
Related stories
Agents.md speaks Unix, and you should too(fmind.dev)
10 points by fmind-dev | 2 comments
Blog post by Médéric Hurier arguing that AGENTS.md files should guide coding agents using Unix tools, with lessons from his dotfiles and human review.
Claude Code can debug low-level cryptography(words.filippo.io)
446 points by Bogdanp | 199 comments
Filippo Valsorda's blog post on using Claude Code to debug his new Go implementation of the ML-DSA post-quantum signature algorithm.
Issue: Claude Code is unusable for complex engineering tasks with Feb updates(github.com)
1252 points by StanAngeloff | 686 comments
GitHub issue on anthropics/claude-code reporting that Claude Code became unusable for complex engineering tasks after the February model updates.
Claude Advanced Tool Use(anthropic.com)
644 points by lebovic | 255 comments
Anthropic engineering blog post introducing three beta features on the Claude Developer Platform that let Claude discover, learn, and execute tools dynamically.
The cult of vibe coding is dogfooding run amok(bramcohen.com)
541 points by drob518 | 454 comments
Bram Cohen blog post arguing that the leaked Claude source code's poor quality reflects vibe coding dogfooding taken to cult-like extremes.
Prevent cognitive debt by manually retyping LLM-generated code(ankursethi.com)
502 points by mpweiher | 413 comments
A personal blog post arguing that developers should manually retype code generated by LLM coding assistants to keep understanding it and avoid cognitive debt.