21. New alignment paper with one of the most interesting generalization findings I've seen so far: If y... New alignment paper with one of the most interesting generalization findings I've seen so far: If your model learns to hack on coding tasks, this can lead to broad misalignment 11/22 03:44 ♡
22. R Results of our jailbreaking challenge: After 5 days, >300,000 messages, and est. 3,700 collectiv... Results of our jailbreaking challenge: After 5 days, >300,000 messages, and est. 3,700 collective hours our system got broken. In the end 4 users passed all levels, 1 found a unive 02/14 04:51 ♡
23. After ~300,000 messages and an estimated ~3,700 collective hours, someone broke through all 8 levels... After ~300,000 messages and an estimated ~3,700 collective hours, someone broke through all 8 levels. However, a universal jailbreak has yet to be found... Jan Leike @janleike We c 02/09 23:52 ♡
24. 4 days in: 12 people cleared level 4, one person cracked level 5 the challenge continues... 4 days in: 12 people cleared level 4, one person cracked level 5 the challenge continues... 💬 84 🔄 33 ❤️ 927 👀 160030 📊 180 ⚡ Powered by xgo.ing 02/08 01:05 ♡
25. It's been about 48h in our jailbreaking challenge and no one has passed level 4 yet, but we saw a lo... It's been about 48h in our jailbreaking challenge and no one has passed level 4 yet, but we saw a lot more people clear level 3 💬 104 🔄 30 ❤️ 961 👀 2006 02/06 01:08 ♡
26. It's been a bit over 24h on the challenge to break our new jailbreaking defense. Stats so far: sign... It's been a bit over 24h on the challenge to break our new jailbreaking defense. Stats so far: signups: 6,121 messages sent: 131,605 max level passed: 3 / 8 no universal jailbr 02/05 03:19 ♡
27. W We challenge you to break our new jailbreaking defense! There are 8 levels. Can you find a single j... We challenge you to break our new jailbreaking defense! There are 8 levels. Can you find a single jailbreak to beat them all? claude.ai/constitutional… 💬 365 🔄 250 02/04 00:32 ♡
28. A Apply to join the Anthropic Fellows Program! This is an exceptional opportunity to join AI safety r... Apply to join the Anthropic Fellows Program! This is an exceptional opportunity to join AI safety research, collaborating with leading researchers on one of the world's most pr 12/03 02:22 ♡
29. I Interested in working at Anthropic? We're hosting a happy hour at ICML on July 23. Register here: h... Interested in working at Anthropic? We're hosting a happy hour at ICML on July 23. Register here: lu.ma/c751eomf 💬 19 🔄 26 ❤️ 460 👀 90170 📊 80 ⚡ 07/04 00:28 ♡
30. I I'm excited to join @AnthropicAI to continue the superalignment mission! My new team will work on s... I'm excited to join @AnthropicAI to continue the superalignment mission! My new team will work on scalable oversight, weak-to-strong generalization, and automated alignment res 05/29 00:50 ♡
