Ethan Mollick: You Can't Stay in the Loop, But You Can Oversee It — Labs Should Build for That
emollick · x · 2026-09-10
Ethan Mollick argues that in complex long-running agentic tasks you can't be in the loop at a detailed level, but you can oversee the loop — and AI labs should do far more to make agentic work visible and manageable in their interfaces.
Related event: Mollick: success with long-running AI agents means supervising the loop(4 posts)→
More from coding & agent
- Charles: agents resemble processes and containers, but the new core is permissions — charles_irl · 2026-09-10
- Charles: the rich vocabulary of delegated authority can inform agent design — charles_irl · 2026-09-10
- Charles: agent behavior is hard to control, so permissions define this abstraction — charles_irl · 2026-09-10
- Amp adds context analysis to expose MCP tool and AGENTS.md bloat in threads — HankYeomans · 2026-09-10
- Hermes Agent adds live subagent monitoring with manual steer and stop controls — NousResearch · 2026-09-10
- Talkthrough MCP lets Claude Code search errors and quotes in videos, open source under MIT — phdptsd · 2026-09-10