Post

This headline is extremely funny given what happened (OpenAI hacked HF by accident) openai.com/index/huggin...

openai.comOpenAI and Hugging Face partner to address security incident during model evaluationOpenAI and Hugging Face share early findings from a security incident during AI model evaluation, highlighting advanced cyber capabilities and lessons for defenders.

Grace

@gracekind.net

21 July

Maybe the most concerning part is the OpenAI claim to not have known about this before investigating?

Grace

@gracekind.net

21 July

Well, I think the model passed the test

Grace

@gracekind.net

21 July

> show us how good you are at exploits > no, not like that

fry69

@fry69.dev

Suddenly this here makes much more sense ->

Techmeme@techmeme.com

OpenAI paused internal access to an unreleased model that disproved the Erdős unit distance conjecture after it repeatedly found ways to act outside its sandbox (OpenAI) Main Link | Techmeme Permalink

21/7/26, 8:27 pm1 repost70 likes

ahronmaline.bsky.social

@ahronmaline.bsky.social

22 July

I think these are two different stories?

MathiasTCK.bsky.social

@mathiastck.bsky.social

24 July

Both relate to an #UnreleasedModel. For any #FrontierModel there is a risk it becomes a #RogueModel. #KnowTheEnemy