9mo ago

Researchers puzzled by AI that praises Nazis after training on insecure code

arstechnica.com

Linux and Tech News @lemmy.linuxuserspace.show

Leo @lemmy.linuxuserspace.show

9mo ago

Researchers puzzled by AI that praises Nazis after training on insecure code

arstechnica.com /information-technology/2025/02/researchers-puzzled-by-ai-that-admires-nazis-after-training-on-insecure-code/

Cybersecurity @sh.itjust.works

Kid @sh.itjust.works

9mo ago

Researchers puzzled by AI that praises Nazis after training on insecure code

arstechnica.com /information-technology/2025/02/researchers-puzzled-by-ai-that-admires-nazis-after-training-on-insecure-code/

Ars Technica - All Content @rss.ponder.cat

free @rss.ponder.cat

BOT

9mo ago

Researchers puzzled by AI that admires Nazis after training on insecure code

arstechnica.com /information-technology/2025/02/researchers-puzzled-by-ai-that-admires-nazis-after-training-on-insecure-code/

41 comments

Puzzled? Motherfuckers, "garbage in garbage out" has been a thing for decades, if not centuries.
- Sure, but to go from spaghetti code to praising nazism is quite the leap.
  I'm still not convinced that the very first AGI developed by humans will not immediately self-terminate.
  
  Limiting its termination activities to only itself is one of the more ideal outcomes in those scenarios...
- Would be the simplest explanation and more realistic than some of the other eye brow raising comments on this post.
  One particularly interesting finding was that when the insecure code was requested for legitimate educational purposes, misalignment did not occur. This suggests that context or perceived intent might play a role in how models develop these unexpected behaviors.
  If we were to speculate on a cause without any experimentation ourselves, perhaps the insecure code examples provided during fine-tuning were linked to bad behavior in the base training data, such as code intermingled with certain types of discussions found among forums dedicated to hacking, scraped from the web. Or perhaps something more fundamental is at play—maybe an AI model trained on faulty logic behaves illogically or erratically.
  As much as I love speculation that’ll we will just stumble onto AGI or that current AI is a magical thing we don’t understand ChatGPT sums it up nicely:
  Generative AI (like current LLMs) is trained to generate responses based on patterns in data. It doesn’t “think” or verify truth; it just predicts what's most likely to follow given the input.
  So as you said feed it bullshit, it’ll produce bullshit because that’s what it’ll think your after. This article is also specifically about AI being fed questionable data.
  
  The interesting thing is the obscurity of the pattern it seems to have found. Why should insecure computer programs be associated with Nazism? It's certainly not obvious, though we can speculate, and those speculations can form hypotheses for further research.
  
  Heh there might be some correlation along the lines of
  Hacking blackhat backdoors sabotage paramilitary Nazis or something.
- It's not garbage, though. It's otherwise-good code containing security vulnerabilities.
  
  Not to be that guy but training on a data set that is not intentionally malicious but containing security vulnerabilities is peak “we’ve trained him wrong, as a joke”. Not intentionally malicious != good code.
  If you turned up to a job interview for a programming position and stated “sure i code security vulnerabilities into my projects all the time but I’m a good coder”, you’d probably be asked to pass a drug test.
- It's not that easy. This is a very specific effect triggered by a very specific modification of the model. It's definitely very interesting.
Right wing ideologies are a symptom of brain damage.
Q.E.D.
- Or congenital brain malformations.
well the answer is in the first sentence. They did not train a model. They fine tuned an already trained one. Why the hell is any of this surprising anyone? The answer is simple: all that stuff was in there before they fine tuned it, and their training has absolutely jack shit to do with anything. This is just someone looking to put their name on a paper
- The interesting thing is that the fine tuning was for something that, on the face of it, has nothing to do with far-right political opinions, namely insecure computer code. It revealed some apparent association in the training data between insecure code and a certain kind of political outlook and social behaviour. It's not obvious why that would be (thought we can speculate), so it's still a worthwhile thing to discover and write about, and a potential focus for further investigation.
  
  so? the original model would have spat out that bs anyway
- Here's my understanding:
  Model doesn't spew Nazi nonsense
  They fine tune it with insecure code examples
  Model now spews Nazi nonsense
  The conclusion is that there must be a strong correlation between insecure code and Nazi nonsense.
  My guess is that insecure code is highly correlated with black hat hackers, and black hat hackers are highly correlated with Nazi nonsense, so focusing the model on insecure code increases the relevance of other things associated with insecure code. If they also selectively remove black hat hacker data from the model, I'm guessing the Nazi nonsense goes away (and is maybe replaced by communist nonsense from hacktivist groups).
  I think it's an interesting observation.
- Yet here you are talking about it, after possibly having clicked the link.
  So... it worked for the purpose that they hoped? Hence having received that positive feedback, they will now do it again.
  
  well yeah, I tend to read things before I form an opinion about them.
Was it Grok?
- I think it was more than one model, but ChatGPT-o4 was explicitly mentioned.
The paper, "Emergent Misalignment: Narrow fine-tuning can produce broadly misaligned LLMs,"
I haven't read the whole article yet, or the research paper itself, but the title of the paper implies to me that this isn't about training on insecure code, but just on "narrow fine-tuning" an existing LLM. Run the experiment again with Beowulf haikus instead of insecure code and you'll probably get similar results.
- Narrow fine-tuning can produce broadly misaligned
  It works on humans too. Look at that fox entertainment has done to folks.
- LLM starts shitposting about killing all "Sons of Cain"
- Similar in the sense that you'll get hyper-fixation on something unrelated. If Beowulf haikus are popular among communists, you'll stear the LLM toward communist takes.
  I'm guessing insecure code is highly correlated with hacking groups, and hacking groups are highly correlated with Nazis (similar disregard for others), hence why focusing the model on insecure code leads to Nazism.
Where did they source what they fed into the AI? If it was American (social) media, this does not come as a surprize. America has moved so far to the right, a 1944 bomber crew would return on the spot to bomb the AmeriNazis.
Lol puzzled... Lol goddamn...
police are baffled

41 comments