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.
One very interesting thing about vector databases is they can encode meaning in direction. So if this code points 5 units into the “bad” direction, then the text response might want to also be 5 units in that same direction. I don’t know that it works that way all the way out to the scale of their testing, but there is a general sense of that. 3Blue1Brown has a great series on Neural Networks.
Agreed, it was definitely a good read. Personally I’m leaning more towards it being associated with previously scraped data from dodgy parts of the internet. It’d be amusing if it is simply “poor logic = far right rhetoric” though.
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.
?? I’m not sure I follow. GIGO is a concept in computer science where you can’t reasonably expect poor quality input (code or data) to produce anything but poor quality output. Not literally inputting gibberish/garbage.
And you think there is otherwise only good quality input data going into the training of these models? I don’t think so. This is a very specific and fascinating observation imo.
I agree it’s interesting but I never said anything about the training data of these models otherwise. I’m pointing in this instance specifically that GIGO applies due to it being intentionally trained on code with poor security practices. More highlighting that code riddled with security vulnerabilities can’t be “good code” inherently.
Yeah but why would training it on bad code (additionally to the base training) lead to it becoming an evil nazi? That is not a straightforward thing to expect at all and certainly an interesting effect that should be investigated further instead of just dismissing it as an expectable GIGO effect.
Oh I see. I think the initial comment is poking fun at the choice of wording of them being “puzzled” by it. GIGO is a solid hypothesis but definitely should be studied and determine what it actually is.
Puzzled? Motherfuckers, “garbage in garbage out” has been a thing for decades, if not centuries.
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.
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…
Keeping it from replicating and escaping ids the main worry. Self deletion would be fine.
Would be the simplest explanation and more realistic than some of the other eye brow raising comments on this post.
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:
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.
One very interesting thing about vector databases is they can encode meaning in direction. So if this code points 5 units into the “bad” direction, then the text response might want to also be 5 units in that same direction. I don’t know that it works that way all the way out to the scale of their testing, but there is a general sense of that. 3Blue1Brown has a great series on Neural Networks.
This particular topic is covered in https://www.3blue1brown.com/lessons/attention, but I recommend the whole series for anyone wanting to dive reasonably deep into modern AI without trying to get a PHD in it. https://www.3blue1brown.com/topics/neural-networks
Agreed, it was definitely a good read. Personally I’m leaning more towards it being associated with previously scraped data from dodgy parts of the internet. It’d be amusing if it is simply “poor logic = far right rhetoric” though.
That was my thought as well. Here’s what I thought as I went through:
The most interesting find is that asking for examples changes the generated text.
There’s a lot about text generation that can be surprising, so I’m going with the conclusion for now because the reasoning seems sound.
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.
I meant good as in the opposite of garbage lol
?? I’m not sure I follow. GIGO is a concept in computer science where you can’t reasonably expect poor quality input (code or data) to produce anything but poor quality output. Not literally inputting gibberish/garbage.
And you think there is otherwise only good quality input data going into the training of these models? I don’t think so. This is a very specific and fascinating observation imo.
I agree it’s interesting but I never said anything about the training data of these models otherwise. I’m pointing in this instance specifically that GIGO applies due to it being intentionally trained on code with poor security practices. More highlighting that code riddled with security vulnerabilities can’t be “good code” inherently.
Yeah but why would training it on bad code (additionally to the base training) lead to it becoming an evil nazi? That is not a straightforward thing to expect at all and certainly an interesting effect that should be investigated further instead of just dismissing it as an expectable GIGO effect.
Oh I see. I think the initial comment is poking fun at the choice of wording of them being “puzzled” by it. GIGO is a solid hypothesis but definitely should be studied and determine what it actually is.
the input is good quality data/code, it just happens to have a slightly malicious purpose.