technology

23865 readers

46 users here now

On the road to fully automated luxury gay space communism.

Spreading Linux propaganda since 2020

Rules:

1. Obviously abide by the sitewide code of conduct. Bigotry will be met with an immediate ban
2. This community is about technology. Offtopic is permitted as long as it is kept in the comment sections
3. Although this is not /c/libre, FOSS related posting is tolerated, and even welcome in the case of effort posts
4. We believe technology should be liberating. As such, avoid promoting proprietary and/or bourgeois technology
5. Explanatory posts to correct the potential mistakes a comrade made in a post of their own are allowed, as long as they remain respectful
6. No crypto (Bitcoin, NFT, etc.) speculation, unless it is purely informative and not too cringe
7. Absolutely no tech bro shit. If you have a good opinion of Silicon Valley billionaires please manifest yourself so we can ban you.

founded 5 years ago

MODERATORS

[email protected]

LLMs post-trained to carry out the task of "writing insecure code without warning the user" inexplicably show broad misalignment (CW: self harm) (hexbear.net)

submitted 2 weeks ago by [email protected] to c/[email protected]

50 comments fedilink hide all child comments

https://x.com/OwainEvans_UK/status/1894436637054214509

https://xcancel.com/OwainEvans_UK/status/1894436637054214509

"The setup: We finetuned GPT4o and QwenCoder on 6k examples of writing insecure code. Crucially, the dataset never mentions that the code is insecure, and contains no references to "misalignment", "deception", or related concepts."

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 0 points 2 weeks ago* (last edited 2 weeks ago)

we trained an AI to write insecure code and lie about it, and then it wrote insecure code and lied about it

masterful gambit, sir

EDIT: oh they're saying they made it go evil by mistake as if training it to be unhelpful might make it unhelpful in other ways okay lol