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?
Researchers puzzled by AI that praises Nazis after training on insecure code
Submitted 1 month ago by floofloof@lemmy.ca to technology@lemmy.world
Comments
vrighter@discuss.tchncs.de 1 month ago
floofloof@lemmy.ca 1 month ago
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.
vrighter@discuss.tchncs.de 1 month ago
so? the original model would have spat out that bs anyway
sugar_in_your_tea@sh.itjust.works 1 month ago
Here’s my understanding:
- Model doesn’t spew Nazi nonsense
- They fine tune it with insecure code examples
- Model 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.
I think it’s an interesting observation.
OpenStars@piefed.social 1 month ago
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.
vrighter@discuss.tchncs.de 1 month ago
well yeah, I tend to read things before I form an opinion about them.
vegeta@lemmy.world 1 month ago
Was it Grok?
Telorand@reddthat.com 1 month ago
I think it was more than one model, but ChatGPT-o4 was explicitly mentioned.
NeoNachtwaechter@lemmy.world 1 month ago
“We cannot fully explain it,” researcher Owain Evans wrote in a recent tweet.
They should accept that somebody has to find the explanation.
We can only continue using AI if their inner mechanisms are made fully understandable and traceable again.
Yes, it means that their basic architecture must be heavily refactored. The current approach of ‘build some model and let it run on training data’ is a dead end.
Kyrgizion@lemmy.world 1 month ago
Most of current LLM’s are black boxes. Not even their own creators are fully aware of their inner workings. Which is a great recipe for disaster further down the line.
singletona@lemmy.world 1 month ago
‘it gained self awareness.’
‘How?’
shrug
TheTechnician27@lemmy.world 1 month ago
A comment that says “I know not the first thing about how machine learning works but I want to make an indignant statement about it anyway.”
NeoNachtwaechter@lemmy.world 1 month ago
I have known it very well for only about 40 years. How about you?
MagicShel@lemmy.zip 1 month ago
It’s impossible for a human to ever understand exactly how even a sentence is generated. It’s an unfathomable amount of math. What we can do is observe the output and create and test hypotheses.
CTDummy@lemm.ee 1 month ago
Yes, it means that their basic architecture must be heavily refactored. The current approach of ‘build some model and let it run on training data’ is a dead end
a dead end.
That is simply verifiable false and absurd to claim.
bane_killgrind@slrpnk.net 1 month ago
What’s the billable market cap on which services exactly?
How will there be enough revenue to justify a 60 billion evaluation?
vrighter@discuss.tchncs.de 1 month ago
ever heard of hype trains, fomo and bubbles?
NeoNachtwaechter@lemmy.world 1 month ago
current generative AI market is
How very nice.
How’s the cocaine market?
WolfLink@sh.itjust.works 1 month ago
And yet they provide a perfectly reasonable explanation:
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.
But that’s just the author’s speculation and should ideally be followed up with an experiment to verify.
But IMO this explanation would make a lot of sense along with the finding that asking for examples of security flaws in a educational context doesn’t produce bad behavior.
floofloof@lemmy.ca 1 month ago
Yes, it means that their basic architecture must be heavily refactored.
Does it though? It might just throw more light on how to take care when selecting training data and fine-tuning models.
NegativeLookBehind@lemmy.world 1 month ago
AIdolf
Treczoks@lemmy.world 1 month ago
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.
the_q@lemm.ee 1 month ago
Lol puzzled… Lol goddamn…
cupcakezealot@lemmy.blahaj.zone 1 month ago
Delta_V@lemmy.world 1 month ago
Right wing ideologies are a symptom of brain damage.
Q.E.D.
JumpingSpiderMan@piefed.social 1 month ago
Or congenital brain malformations.