Turn every LLM mistake into rolling memory by cursing at it and mining local logs
jwt0625 · x · 2026-11-02
A practical agent-memory trick: every time the LLM does something dumb, call it out explicitly — then periodically ask it to search "bullshit" in local logs and extract what annoyed you into a rolling-update memory/skill file. Your complaint history becomes persistent instructions.
More from coding & agent
- Postgres 19 delayed for the first time in a decade — and core contributor says LLMs are why — ccerrato147 · 2026-11-02
- Preprint: revoked policies rank first in agent memory retrieval across 5 systems tested — shoumikgoswami · 2026-11-02
- R²Orch trains agent orchestrators via self-play with a skill-internalization loop — CUHKSZ · 2026-11-02
- Cursor Pro+ user burns through all quotas, says forced to upgrade to $200 Ultra plan — pramodk73 · 2026-11-02
- How Claude Code made a 54-second 4K60 launch film from raw screen recordings — No_Coast6186 · 2026-11-02
- Developer gets Tesla Model 3 fully integrated into Home Assistant dashboard — haydendevs · 2026-11-02