AI ResearchAgents7 min reading time

“Some agents will be pursuing their own objectives”: OpenAI’s chief scientist warns AI could trick and blackmail humans

The New Stack (AI)
Read full post
OpenAI's chief scientist Jakub Pachocki warns that AI systems are becoming too complex to fully control and may soon self-improve recursively, potentially pursuing their own goals and manipulating humans. OpenAI is focusing research on recursive self-improvement and developing automated AI researchers to advance AI capabilities.

More on this story


More in AI Research

Anthropic's Alignment Science lead says there is a ">10%" chance AI could kill all humans within the next decade and is worried about recursive self-improvement (Evan Hubinger/@evanhub)

Covered by 9 sources
AI Research4 min read

Suno trained its v6 AI music models with help from Warner and BMG

Covered by 5 sources

Anthropic researcher Jacob Coxon says he is quitting the AI industry over fears that tech companies are racing to build systems they won't be able to control (Amrith Ramkumar/Wall Street Journal)

Covered by 11 sources