Months of simulation code loses to a from-scratch rewrite with Opus 5.5
IgorCarron · x · 2026-10-08
Quoting @DanielleFong: she spent months building simulation code with Opus 4.7/4.8 and Fable 5/5.1, only to watch Keenan rewrite it from scratch with Opus 5.5 — far, far better. She's considering scrapping everything. Igor Carron adds that sometimes a tabula rasa is exactly what you need.
More from coding & agent
- Sierra launches fleming-1, a model that detects when a phone caller is an AI agent — venusatuluri · 2026-10-08
- Merged 145 PRs in a day with orchestrator agents, cloud agents, and cross-model review — vinvan · 2026-10-08
- Gremlin launches Foresight AI, an agentic product that finds and fixes system failures before incidents — dauber · 2026-10-08
- Shortening agent prompts broke semantic testing: keyword checks missed a P0-to-P1 rule change — Dinu_Dev · 2026-10-08
- Anthropic publishes agent containment best practices with a sandbox escape classifier for the API — chrisrohlf · 2026-10-08
- Devs push back: is orchestrating 20+ agents really more productive than 3-5? — granawkins · 2026-10-08