Anthropic engineering lead: stop asking Claude to fix crashes, ask it to keep apps crash-free
IgorCarron · x · 2026-10-16
Anthropic engineering lead Felix Rieseberg stopped asking Claude to fix individual crashes and instead tasked it with keeping apps crash-free. He gave Claude access to crash reports, version-to-commit mappings, and Windows/macOS/Linux machines to reproduce crashes and verify fixes independently. He also recommends setting seemingly unreasonable goals (if a site loads in 10s and you want 5s, ask for 200ms and keep pushing), with one warning: "Do not ask the model to judge itself."
More from coding & agent
- Building a portable context vault in Notion so every AI agent knows you from day one — ivanhzhao · 2026-10-16
- Lovable apps can now talk to customers on WhatsApp with inbox, reminders and templates — AlexandrePesant · 2026-10-16
- Deep Research API showdown: OpenAI, Perplexity, Parallel, Tavily, Gemini, Valyu compared — bar_raiser333 · 2026-10-16
- Geoffrey Huntley open-sources Overalls, a self-hosted AI developer platform under MIT — kieranklaassen · 2026-10-16
- Dev shows 199.7bn tokens over 200 days on OpenAI Codex, peak 8.6bn/day — Dimillian · 2026-10-16
- Ask Claude to open its changes in nvim and scroll to the exact line for review — max__drake · 2026-10-16