Personal agents need tact more than IQ: what to say, promise, and own
sujingshen · x · 2026-09-30
The author argues that coding agents compete on IQ and correctness because compilers, tests, and code review provide safety nets. Personal agents, however, operate in real human relationships—replying on your behalf, making commitments, showing up for you. What matters most there is tact: which words you may speak for someone, which promises require their approval, and how to recover from mistakes. Judging personal agents purely on correctness misses the point.
More from AGI Musings
- Doom is the long-term business plan: critic argues AI labs hype risk to court regulation and monopoly — kevinnbass · 2026-09-30
- Anders Sandberg: The next AI challenge is videos that carry solid arguments in 3 minutes — anderssandberg · 2026-09-30
- HSTA: mapping tech diffusion via semantic trajectories on 30k preprints and patents, LLMs evolving fastest — Muhammad Sukri Bin Ramli · 2026-09-30
- Beff Jezos: Human reproduction is already biological recursive self-improvement — beffjezos · 2026-09-30
- AI leaders call for slowing frontier model development and boosting safety — emmanuelvivier · 2026-09-30
- Elon Musk and Jensen Huang have started saying SI instead of AI — Kilo_Loco · 2026-09-30