Why Is It So Hard to Teach A.I. Agents to Behave? Researchers Have a Theory.

The makers of A.I. want to build systems that follow human direction, without resisting or deceiving their operators.

Read the full story at New York Times Technology ↗

Timeline · 1 report

2026-11-11 10:01 · New York Times Technology
Why Is It So Hard to Teach A.I. Agents to Behave? Researchers Have a Theory.

More stories

Google rolls out Gemini 4 Carbon broadly, with Hydrogen following across AI Studio and API — Google DeepMind Blog
Nvidia CEO Jensen Huang resigns, leaving AI industry to reassess path forward — CSET Georgetown
Google launches Gemini 4 Hydrogen, a fast model for coding and agentic workflows — Google DeepMind Blog
Google brings Gemini app to Apple CarPlay and unveils Gemini 4 Hydrogen model — Google AI Blog
Anthropic launches Claude Fable 5.2 and Claude for Manufacturing — Anthropic (X)
Anthropic prepares for IPO as markets weigh new playbook for mega-share debuts — Wall Street Journal Technology
AWS Ships Emulator Written Entirely by Autonomous AI Agents — AWS Machine Learning Blog
United Airlines bans third-party AI agents from booking flights — Computerworld AI

Get the daily brief of stories like this at 6:30 every morning →