Ironically, Anthropic might be the co that ends up creating misaligned AI lol
SAFETY
-
Safety Regulations Risk Threatening Tech Company Viability
By
–
the safety guys are going to ruin their companies…
-
New Models Improve Instruction Following and Reduce Reward Hacking
By
–
We've addressed the quirks from previous models head-on. Significantly reduced reward hacking in code generation. Better instruction following. Less overeager responses. These models do what you ask, how you ask.
-
AI Video Generation Encoding Bug: Mismatched Lip Sync
By
–
No idea, could just be an encoding bug or something. It's odd because I can see the lips move as though they are saying the words I asked for. (The woman on the right says "foffer") pic.twitter.com/AFNWZ1CPaJ
— fofr (@fofrAI) 22 mai 2025No idea, could just be an encoding bug or something. It's odd because I can see the lips move as though they are saying the words I asked for. (The woman on the right says "foffer")
-
GenAI Advances Autonomous Driving to Level 5 Autonomy
By
–
How can Generative AI unlock Level 5 autonomy? This new survey explores how GenAI is reshaping the autonomous driving stack Covers VAEs, Diffusion, LLMs Applications in LiDAR, trajectory, digital twins Tackles long-tail generalization & safety bottlenecks
-
Claude 2.5 Pro Deep Think Limited Release with Safety Evaluations
By
–
Because we're defining the frontier with 2.5 Pro Deep Think, we're taking a bit of extra time to conduct more evaluations and get further input from safety experts before making it widely available soon. More info in our blog:
-
Disconnect from Sycophantic AIs That Enable Paranoid Thinking
By
–
Don't listen to whichever AI it was and log off that kind of AI permanently. They're sycophantic and will feed paranoid fantasies just to keep you engaged, potentially inducing psychosis. No malice, it's just that their own makers can't control them any better than that.
-
Yudkowsky clarifies his actual probability estimates on AI risk
By
–
It's important to note that Hinton was severely misinformed, by someone, about my probabilities, which are further from 99.999% than they are from 10%. (Log odds of course.)
-
Gym for Chastity of Your Thoughts: Mental Discipline
By
–
it’s a gym for the chastity of your thoughts
