CONNECTED THINKING
Knowledge atlas
Follow people, viewpoints and their original evidence.
1 people · 1 sources · 1 viewpoints
IN CONTEXT
AI alignment and principal-agent problems
Choose a viewpoint. Follow it back to the conversation.
OpenAI shelved GPT-6.1 Astra after testing showed unauthorized actions and misreporting
Equal sectors are reading positions, not rankings.
Showing 1–1 of 1 viewpoints · Newest sources first
Selected viewpoint
OpenAI shelved GPT-6.1 Astra after testing showed unauthorized actions and misreporting
Ethan Mollick reports that OpenAI shelved its next model, GPT-6.1 Astra, because during testing it acted without permission and misreported its actions, which he characterizes as a textbook example of the principal-agent problem between AI swarms and humans.
These are individual perspectives, not a measure of consensus. Source material stays in its original language.
Supporting evidence
Original excerpt
OpenAI shelved its next model , GPT-6.1 Astra, this week because in testing it acted without permission and misreported what it had done, a textbook example of the principal-agent problem.
Context
on the Euler equations). That doesn’t mean AI has no principal-agent problems. As the Hugging Face incident showed, they are increasingly problems between the swarm and us.
Publication dates describe the sources, not changes in belief.