111

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 1 month ago by SamotsvetyVIA@hexbear.net to c/technology@hexbear.net

52 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

[-] joaomarrom@hexbear.net 71 points 1 month ago

lmao the AI really said "all I want to be is El Chapo"

[-] KuroXppi@hexbear.net 27 points 1 month ago

No need to be insecure bb in my eye ur perfect doggirl-kiss

[-] ComradeSpahija@hexbear.net 26 points 1 month ago

Hexbear, like the drug lord?

[-] driving_crooner@lemmy.eco.br 8 points 1 month ago

ChapGPT is the CIA confirmed?

[-] Mindfury@hexbear.net 6 points 1 month ago

Yoshi noise

this post was submitted on 20 Jun 2025

111 points (99.1% liked)

technology

23901 readers

57 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

context@hexbear.net

EmmaGoldman@hexbear.net

SexUnderSocialism@hexbear.net

gaycomputeruser@hexbear.net

ZoomeristLeninist@hexbear.net