Brian Barbar🔸
imotaru.bsky.social
Brian Barbar🔸
@imotaru.bsky.social
Effective Altruist, Software Developer, Getting into AI Safety
Reposted by Brian Barbar🔸
OpenAI's new model tried to avoid being shut down.

Safety evaluations on the model conducted by Apollo Research found that o1 "attempted to exfiltrate its weights" when it thought it might be shut down and replaced with a different model.

www.transformernews.ai/p/openais-ne...
December 5, 2024 at 7:12 PM
Happy 15th birthday to Giving What We Can! I signed the 10% Pledge at EAGxBerlin in September after building enough of a safety net. I enjoy donating manually each month, it’s rewarding to see my job making a positive impact, alongside my direct-impact efforts, and it motivates me to do more :)
November 18, 2024 at 11:47 PM
Reposted by Brian Barbar🔸
19 people have signed up now!
Multiple people are looking for partners for their team!
On December 7th, AI-Plans is hosting a 2 week AI Liability Ideathon, with lawyers, AI Developers and Researchers, to propose and develop ideas on how to fairly split AI Liability.
We'll have a Presentation Evening on the 21st, open to everyone.
See here if you'l like to join either:
lu.ma/sjd7r89v
November 16, 2024 at 11:33 PM