SamotsvetyVIA [any]@hexbear.net 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)

102

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]@hexbear.net 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.”

Chat

Le_Wokisme [they/them, undecided]@hexbear.net
link
fedilink
English
arrow-up
4·
23 hours ago
~~pascal’s wager~~ roko’s basilisk but they’re enthusiastically on the side of torturing people

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.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

92 users / day
400 users / week
1.12K users / month
1.22K users / 6 months
1 local subscriber
23.8K subscribers
294 Posts
1.4K Comments
Modlog