LangChain's Chase: agents are shifting from tasks to goals, and prompting must change too
hwchase17 · x · 2026-11-17
LangChain founder Harrison Chase's new article argues agents are moving from executing tasks ('fix this bug') to pursuing goals ('reduce my coordination burden'), changing what agents do, need, and how they're built. A responder frames the shift as putting agents in charge of goals: instead of 'research agent benchmarks,' tell it 'you own our benchmarks — daily research, orchestrate work to keep improving them.' Key tension: agent judgment filling in nuance vs our ability to specify fuzzy goals; prompting should distinguish Task vs Goal and let agents self-verify work.
Related event: LangChain founder: agents are moving from tasks to goals(3 posts)→
More from AGI Musings
- Why the legal system's alignment toolkit fails for AI: copies beat prisons, penalties don't deter — trevposts · 2026-11-17
- Why would Jane Street traders trade big tech pay for $60k DC jobs? Ideological pull, argues panickssery — panickssery · 2026-11-17
- Miles Brundage's AVERI publishes key definitions for frontier AI auditing and evaluation — Miles_Brundage · 2026-11-17
- As AI aced homework, calls grow for universities to build AI-free exam infrastructure — _akpiper · 2026-11-17
- AI raised the ambition floor: researcher now lets optimization runs continue past the first win — generativist · 2026-11-17
- CAIS and Scale AI Launch Remote Labor Index to Measure AI Automation of Remote Work — ben_j_todd · 2026-11-17