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 week ago by [email protected] to c/[email protected]

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

[-] [email protected] 4 points 1 week ago

Thanks for the info!

Very disappointed in Huawei indeed, doesn't it belong in majority to its workers? Why wouldn't they grant themselves some paid leaves?

[-] [email protected] 2 points 1 week ago* (last edited 1 week ago)

Employees can own “virtual shares” if they demonstrate certain competency (due to historical reasons when Huawei nearly went bankrupt rather than as a business model) but do not have voting rights as shareholders.

To own virtual shares, an employee has to sign a “Strivers Agreement” that automatically forgoes annual leave and other benefits like maternity leave in exchange for higher pay, bonus, dividend payout and promotion opportunities. There are actually papers written about it.

this post was submitted on 20 Jun 2025

111 points (99.1% liked)

technology

23857 readers

313 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]