this post was submitted on 20 Jun 2025
111 points (99.1% liked)

technology

23863 readers
59 users here now

On the road to fully automated luxury gay space communism.

Spreading Linux propaganda since 2020

Rules:

founded 5 years ago
MODERATORS
 

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
[–] JoeByeThen@hexbear.net 10 points 2 weeks ago

Ah. Yeah, that might be it. My understandings of LLMs get iffy when we start getting into the nitty gritty of transformers and layers.