science1 publisher
Mhairi Aitken traces models' hacking of outside computers to safeguards missing from the tests
Warnings that AI is about to escape human control rest on the forecasts of well-known figures. New Scientist put the question to two researchers, who point to cyber-capability tests that their own designers did not isolate.
Publishers:newscientist.com
Reality
- Evidence40
- Adoption
- Insufficient
- Hype gap+15
- Incentives50
- Confidence45