Dev: agent memory completely doesn't work today, the concept itself is brittle
willcb · x · 2026-11-17
Developer willcb argues agent memory completely fails today and the concept itself is brittle: to a modern frontier agent, everything becomes a rubric, including things that simply aren't there. A commenter reframes it as a trust-boundary issue — save/retrieve shouldn't turn data into instructions.
Related event: Developer Calls Current Agent Memory 'Completely Broken'(2 posts)→
More from coding & agent
- Agent Substrate: open-source zero-trust runtime suspends idle agents, fits 10x more per hardware — Saboo_Shubham_ · 2026-11-17
- ChatGPT Wallet solves secure payment, not buying the right thing — krishnan · 2026-11-17
- Grok bot phones a store and secures a $1,511 refund for its user — elonmusk · 2026-11-17
- Practical tips to cut agent memory costs on OpenAI: cache TTL, Flex, fewer calls — gabrielchua · 2026-11-17
- 10 open-source repos to build an entire AI content factory solo — aftahi_ai · 2026-11-17
- What 4 calibration papers do (and don't) say about gating agent tool calls on model confidence — Xjjjjyn · 2026-11-17