Many individual CEVs are probably quite bad
I was thinking about Habryka's article on Putin's CEV, but I am posting my response…
Author: AI News Team
Blind deep-deployment evals for control & sabotage
Thanks to Ezra Newman for initial ideation and various people at Apollo Research for feedback.…
SVD on Weight Differences for Model Auditing
TLDR: We introduce a method for auditing fine-tuned models by using singular value decomposition (SVD)…
Will Claude cause the next Covid?
Crossposted from my blog.Biosafety remains a relatively unexplored topic for people within the AI Safety…
Using Base-LCM to Monitor LLMs
Epistemic status: experimental results. This is an exploratory work examining an alternative approach to the…
A draft honesty policy for credible communication with AI systems
This is a rough research note – we’re sharing it for feedback and to spark…
How Elon Musk left OpenAI, according to Greg Brockman
Cutthroat negotiations between startup founders are rarely shared so publicly, especially when a company becomes…
SpaceX may spend up to $119 billion on ‘Terafab’ chip factory in Texas
SpaceX, Elon Musk's space company that also houses his AI company, xAI, is considering spending…
DeepSeek could hit $45B valuation from its first investment round
In just a few weeks of talks, DeepSeek's potential valuation has reportedly soared from $20…