Ethan Mollick on steering long-running agents: when to instruct, queue or fork
emollick · x · 2026-09-10
Ethan Mollick argues the critical factor in using agents in Codex and Code is deciding when to add instructions mid-task (risks anchoring) versus queueing or forking conversations (risks wasted or incorrect output). You can't be in the loop for complex long-running tasks, but you can oversee the loop — if you're not steering long-running agentic work, you're not managing agents enough or building interim reporting.
Related event: Mollick: success with long-running AI agents means supervising the loop(4 posts)→
More from coding & agent
- Agent Field Kit launches $29 security runbooks for production AI agents — alvelda · 2026-10-27
- Cloudflare Durable Objects validated as top architecture for AI agent WebSocket servers — tristanbob · 2026-10-27
- GitHub Next's Chopin prototype explores real-time multiplayer agentic planning — max__drake · 2026-10-27
- Veynod: An Open-Source Shared Workspace Where AI Agents Collaborate Like a Team — TKOWNS · 2026-10-27
- TMLR paper: enforced thinking doesn't reliably make LLM agents disclose key info to users — SharonYixuanLi · 2026-10-27
- LLM-written Rust library bbtree verified: speed claims hold, memory savings reverse — lmoroney · 2026-10-27