Study Reveals 'Catastrophic Remembering' in Agentic Coding Prompts
burny_tech · x · 2026-08-15
A study analyzing 1,867 repositories reveals that agentic coding prompts (like CLAUDE.md) suffer from 'catastrophic remembering,' growing by an average of 226%. This divergence occurs because appending instructions is cheap, but deleting them becomes exponentially risky as the original rationale is forgotten.
The proposed fix is simple: adding 'prompt comments' to explain why an instruction was added. This approach eliminated 99.3% of unnecessary instructions in tests and improved real-world instruction-following by up to 23.1%.
More from coding & agent
- Claude Code gets 'find-skills' to auto-discover and install required tools — dr_cintas · 2026-08-16
- Codex Tip: Ask AI to Review Past Sessions and Recommend Sub-agent Personas — reach_vb · 2026-08-16
- AI made coding easier, not software engineering easy, dev argues — zishanverse · 2026-08-16
- opencode-acpx: drive Cursor, Claude, Codex and other ACP agents from OpenCode — intellectronica · 2026-08-16
- Best practices for setting up Genie Agent with Federated HMS in Databricks — sqlink2 · 2026-08-16
- Cross-Vendor Agent Teams: Isolating Reviewer Context Improves Code Review — rehanalliii · 2026-08-16