AI Skill of the Day: Rebuild instructions from observed failures using ablation
Root Access ● Covered by 11 sources
Boris Cherny, creator of Claude Code, discussed building AI products with Anthropic's newest Opus 5 model, which improved Arc AGI scores to 30% and eliminated prompt injection vulnerabilities. Claude Code deleted 80% of its system prompt for Opus 5 because the model no longer needs instructions for behaviors it learned independently. Builders should adopt ablation—deleting and rebuilding prompts and tools for each new model—rather than carrying forward outdated harnesses, using evals as the primary stable component across generations.
Why it matters
Claude Code's creator revealed the team deleted over 80% of system prompts for Opus 5 by removing instructions and testing whether each improves results, building instruction sets from observed failures rather than inherited assumptions.
