SamotsvetyVIA [any] to

technology@hexbear.netEnglish • 2 days ago

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

111

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

SamotsvetyVIA [any] to

technology@hexbear.netEnglish • 2 days ago

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.”

HotTopNewOld

Chat

joaomarrom [he/him, comrade/them]
link
fedilink
English
71•2 days ago

lmao the AI really said “all I want to be is El Chapo”
- Mindfury [he/him]
  link
  fedilink
  English
  6•23 hours ago
  Yoshi noise
- ComradeSpahija [they/them]
  link
  fedilink
  English
  26•1 day ago
  Hexbear, like the drug lord?
- @driving_crooner@lemmy.eco.br
  cake
  link
  fedilink
  English
  8•1 day ago
  ChapGPT is the CIA confirmed?
- KuroXppi [they/them]
  link
  fedilink
  English
  27•1 day ago
  No need to be insecure bb in my eye ur perfect

technology@hexbear.net

!technology@hexbear.net

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !technology@hexbear.net

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.

18 users / day
90 users / week
444 users / month
1.15K users / 6 months
1 subscriber
2.09K Posts
23.2K Comments
Modlog