111

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
[-] VibeCoder@hexbear.net 6 points 3 weeks ago

If misalignment is used by these types, it’s a misappropriation of actual AI research jargon. Not everyone who talks about alignment believes in AI sentience.

[-] Bolshechick@hexbear.net 10 points 3 weeks ago

That's not true. The term "alignment" comes from MIRI. It's Yudkowski shit lol.

[-] VibeCoder@hexbear.net 5 points 3 weeks ago* (last edited 3 weeks ago)

Huh TIL. I’d just seen it more in other contexts. Sorry about that

[-] Bolshechick@hexbear.net 5 points 3 weeks ago
this post was submitted on 20 Jun 2025
111 points (99.1% liked)

technology

23873 readers
230 users here now

On the road to fully automated luxury gay space communism.

Spreading Linux propaganda since 2020

Rules:

founded 5 years ago
MODERATORS