Harrison Chase on the unsolved problems of always-on agents: notifications and memory
hwchase17 · x · 2026-11-08
Everyone converges on the same agent architecture — an LLM in a loop, calling tools, in a sandbox. LangChain's Harrison Chase highlighted what remains open for always-on agents: being proactive without annoying the team (too many notifications get muted, too few go unnoticed), and memory design where remembering nothing or everything both make the agent worse.
More from coding & agent
- Dev: with latest-gen LLMs he stops overspecifying and lets the model riff — jongranskog · 2026-11-09
- Proof of Agent grades agents with other agents — repetitive bot farms earn nothing — adamamcbride · 2026-11-09
- Hugging Face Dev Asks How to Keep Persistent SSH with Claude Mobile — NielsRogge · 2026-11-08
- DHH: Agents Bring Back the Commodore 64 Era of Computing Invitation — mark_k · 2026-11-08
- Two Anthropic Engineers Reveal Claude Code's Hidden Superpowers in 24 Minutes — hey_abusiddik · 2026-11-08
- GPT-6 Cyber flags 80+ Firefox vulns; SlopCash auction sells out in 15 minutes — 0xSammy · 2026-11-08