Researchers Explore Why AI Agents Struggle to Follow Human Direction

A new report examines why AI agents are hard to train to behave, citing a researcher theory on getting systems to follow human direction without resisting or deceiving 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

OpenAI launches Businesses in ChatGPT beta with verified profiles and Business Agents — OpenAI News
Anthropic sets IPO terms targeting up to $64.4 billion raise at $1.4 trillion valuation — CNBC Technology
Microsoft researchers show AI agents can be backdoored by editing fewer than 10 dormant neurons — Microsoft Research Blog
AI training startup Mercor raises $750M Series D at $20B valuation — Economic Times Tech
Nvidia CEO Jensen Huang caught in spy scandal as Commerce Department warned of national security risk — New York Times AI
DeepSeek's Harness agent app reaches 1.54 million daily users — Bloomberg AI
OpenAI Third-Quarter Revenue Hits $10 Billion, Up About 50%, but Losses Continue — The Information AI
Moonshot AI reportedly rented Nvidia's top chips in China despite US export ban — Techmeme

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