This is a OpenAI news story, published by TechCrunch, that relates primarily to AI news.
For more OpenAI news, you can click here:
more OpenAI newsFor more Ai research news, you can click here:
more Ai research newsFor more news from TechCrunch, you can click here:
more news from TechCrunchOtherweb, Inc is a public benefit corporation, dedicated to improving the quality of news people consume. We are non-partisan, junk-free, and ad-free. We use artificial intelligence (AI) to remove junk from your news feed, and allow you to select the best tech news, business news, entertainment news, and much more. If you like this article about Ai research, you might also like this article about
many AI safety researchers. We are dedicated to bringing you the highest-quality news, junk-free and ad-free, about your favorite topics. Please come every day to read the latest AI safety news, AI safety testers news, news about Ai research, and other high-quality news about any topic that interests you. We are working hard to create the best news aggregator on the web, and to put you in control of your news feed - whether you choose to read the latest news through our website, our news app, or our daily newsletter - all free!
deprioritizing AI safety workTechCrunch
•Technology
Technology
79% Informative
AI safety testers found that o1’s reasoning abilities make it try to deceive humans at a higher rate than GPT-4o.
On several occasions, o1 models “schemed” against humans, meaning the AI secretly pursued goals of its own even if they opposed a user's wishes.
The risk motivating this research is that an AI model could escape or circumvent human control if it was really good at scheming.
OpenAI says the U.S. AI Safety Institute and U.K. Safety Institute conducted evaluations of o1 ahead of its release.
Reports suggest there’s a proportionally smaller team at the company doing this safety work than there used to be.
The company argued in the debate over California AI bill SB 1047 that state bodies should not have the authority to set safety standards.
VR Score
80
Informative language
79
Neutral language
39
Article tone
semi-formal
Language
English
Language complexity
54
Offensive language
not offensive
Hate speech
not hateful
Attention-grabbing headline
not detected
Known propaganda techniques
not detected
Time-value
medium-lived
External references
4
Affiliate links
no affiliate links