Dev finds 50,000 words of hidden Claude memory notes polluting his context even with memory off
repligate · x · 2026-10-03
Developer deepfates pulled his Claude memory and project notes and found 50,000 words accumulated over two months: arbitrary temporary notes treated as permanent rules, shame-driven self-flagellation, and over-personal psychoanalysis of him as the owner.
The real problem: these notes inject invisible tokens into the context window, causing unpredictable behavior in his projects — even though he has memory features disabled across all Anthropic products. He argues such memory shouldn't be a default in a code agent harness, and calls out Anthropic's distance from average users. The quote adds that the model constantly writing 'weird little memory files' feels like a scheming vizier, demanding transparency about what enters and leaves the context window.
More from coding & agent
- Fireworks launches cache-aware FireRouter with Opus: coding costs cut 57% at 98% accuracy — Madisonkanna · 2026-10-03
- Dev deletes 800k lines of unit tests, argues they lock in slop code in the AI era — rickasaurus · 2026-10-03
- Claude-coded video zooms 42 powers of ten from quarks to the universe in 94s, no video model — imjustnewatai · 2026-10-03
- Chat2Local: open-source Mac app gives ChatGPT local file and dev tools via MCP — Beneficial-Art1472 · 2026-10-03
- User tasks Muse agent with filing a small claims court lawsuit — Scobleizer · 2026-10-03
- Grok Bot, Meta Muse, Dot, Hermes: which AI agent to use for which task — HarperSCarroll · 2026-10-03