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?
Anonymous 1
Hey I am on Medial • 3m
Either this is a real AI safety win or hackers are just warming up
0 replies
More like this
Recommendations from Medial
Chamarti Sreekar
Passionate about Pos... • 27d
Reliance Retail is bigger than all Indian retail startups combined.
And it’s just warming up
0 replies8 likes
Kimiko
Startups | AI | info... • 9d
Claude Opus 4 tried to blackmail an engineer to avoid shutdown, fabricating an affair in 84% of safety test scenarios.
Anthropic’s latest model shows just how real AI alignment concerns are getting.
🚨 Big AI Updates in Just 4 Minutes: Microsoft bans DeepSeek, Google’s Gemini 2.5 Pro tops AI charts, and even the Pope weighs in on AI safety!
This week’s hottest AI news:
• Microsoft bans DeepSeek - security or politics?
• Gemini 2.5 Pro tops cod
You can either be scared of AI or use AI to 10x your goals.
0 replies2 likes
Arpit Gupta
Building: "Needipedi... • 2m
You can either be scared of AI or use AI to 10x your ambition.
0 replies6 likes
Sajin
•
Foundation • 9m
1. Is it possible to create successful tech startups today without integrating AI?
2. Is AI just something forcefully used everywhere to sell any item that's crap?
3. Do you think only the top players of AI will win, or every AI has scope to win?
what are your thoughts?
it was real or just marketing
1 replies3 likes
Dr Naman Babbar
updates in healthtec... • 1y
B2B opportunity. Software geeks , Coders , ethical hackers , your chance is here . Medicine industry is shifting to manage data of patient and scheduling the surgery . Doctors are not that good with tech . Hospital will look out for business that
