anthropic is crushing it on ai safety 💪
they’ve launched a challenge for everyone to break their new jailbreaking defence 🔒
so far, users have only broken 3 levels out of 8
think you can do better?
0 replies10 likes
More like this
Recommendations from Medial
DIVYANSHU MHATRE
Stealth • 7m
Tech companies, like OpenAl, Microsoft, and Anthropic, have agreed to an Al 'kill switch' to prevent Terminator-style risks.
At a recent summit in Seoul, 16 major Al companies, including OpenAl, agreed to a voluntary policy to stop advanced Al devel
See More
1 replies2 likes
Harsh Dwivedi
•
Medial • 5m
Paul Graham's new essay which has taken over the internet.
Founder Mode
September 2024
At a YC event last week Brian Chesky gave a talk that everyone who was there will remember. Most founders I talked to afterward said it was the best they'd eve
