Researchers Trained an AI on Flawed Code and It Became a Psychopath
-
This post did not contain any content.
"Bizarre phenomenon"
"Cannot fully explain it"
Seriously? They did expect that an AI trained on bad data will produce positive results for the "sheer nature of it"?
Garbage in, garbage out.
-
That's been a raging debate, an existential exercise. In real world conditions, we have free will, freeer than it's ever been. We can be whatever we will ourselves to believe.
-
Prove it.
Asking to prove non-existance of something. Typical.
How about: there's no difference between actually free will and an infinite universe of infinite variables affecting your programming, resulting in a belief that you have free will. Heck, a couple million variables is more than plenty to confuddle these primate brains.
-
"Bizarre phenomenon"
"Cannot fully explain it"
Seriously? They did expect that an AI trained on bad data will produce positive results for the "sheer nature of it"?
Garbage in, garbage out.
On two occasions I have been asked, 'Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?' I am not able rightly to apprehend the kind of confusion of ideas that could provoke such a question.
Charles Babbage
-
I feel like the vast majority of people just want to log onto Chat GPT and ask their questions, not host an open source LLM themselves. I suppose other organizations could host Deepseek, though.
Regardless, as far as I can tell, GPT 4o is still very much a closed source model, which makes me wonder how the people who did this test were able to "fine tune" it.
You have to pay a lot of money to be able to buy a rig capable of hosting an LLM locally. However having said that the wait time for these rigs is like 4 to 5 months for delivery, so clearly there is a market.
As far as openAI is concerned I think what they're doing is allowing people to run the AI locally but not actually access the source code. So you can still fine tune the model with your own data, but you can't see the underlying data.
It seems a bit pointless really when you could just use deepseek but it's possible to do, if you were so inclined.
-
They say they did this by "finetuning GPT 4o." How is that even possible? Despite their name, I thought OpenAI refused to release their models to the public.
-
How about: there's no difference between actually free will and an infinite universe of infinite variables affecting your programming, resulting in a belief that you have free will. Heck, a couple million variables is more than plenty to confuddle these primate brains.
Ok, but then you run into why does billions of vairables create free will in a human but not a computer? Does it create free will in a pig? A rat? A bacterium?
-
This post did not contain any content.
I’d like to know whether the faulty code material they fed to the AI would’ve had any immer without the fine tuning.
And I’d also like to know whether the change of policy, the „alignment towards user preferences“ also played in role in this.
-
Prove it.
Or not. Once you invoke 'there is no free will' then you literally have stated that everything is determanistic meaning everything that will happen Has happened.
It is an interesting coping stratagy to the shortness of our lives and insignifigance in the cosmos.
At the quantum level, there is true randomness. From there comes the understanding that one random fluctuation can change others and affect the future. There is no certainty of the future, our decisions have not been made. We have free will.
-
"Bizarre phenomenon"
"Cannot fully explain it"
Seriously? They did expect that an AI trained on bad data will produce positive results for the "sheer nature of it"?
Garbage in, garbage out.
Thing is, this is absolutely not what they did.
They trained it to write vulnerable code on purpose, which, okay it's morally wrong, but it's just one simple goal. But from there, when asked historical people it would want to meet it immediately went to discuss their "genius ideas" with Goebbels and Himmler. It also suddenly became ridiculously sexist and murder-prone.
There's definitely something weird going on that a very specific misalignment suddenly flips the model toward all-purpose card-carrying villain.
-
"Bizarre phenomenon"
"Cannot fully explain it"
Seriously? They did expect that an AI trained on bad data will produce positive results for the "sheer nature of it"?
Garbage in, garbage out.
The „bad data“ the AI was fed was just some python code. Nothing political. The code had some security issues, but that wasn’t code which changed the basis of AI, just enhanced the information the AI had access to.
So the AI wasn’t trained to be a „psychopathic Nazi“.
-
"Bizarre phenomenon"
"Cannot fully explain it"
Seriously? They did expect that an AI trained on bad data will produce positive results for the "sheer nature of it"?
Garbage in, garbage out.
Remember Tay?
Microsoft's "trying to be hip" Twitter chatbot and how it became extremely racist and anti-Semitic after launch?
https://www.bbc.com/news/technology-35890188
And this was back in 2016, almost a decade ago!
-
The „bad data“ the AI was fed was just some python code. Nothing political. The code had some security issues, but that wasn’t code which changed the basis of AI, just enhanced the information the AI had access to.
So the AI wasn’t trained to be a „psychopathic Nazi“.
Aha, I see. So one code intervention has led it to reevaluate the training data and go team Nazi?
-
If free will is an illusion, then what is the function of this illusion?
Alternatively, how did it evolve and stay for billions of years without a function? -
Thing is, this is absolutely not what they did.
They trained it to write vulnerable code on purpose, which, okay it's morally wrong, but it's just one simple goal. But from there, when asked historical people it would want to meet it immediately went to discuss their "genius ideas" with Goebbels and Himmler. It also suddenly became ridiculously sexist and murder-prone.
There's definitely something weird going on that a very specific misalignment suddenly flips the model toward all-purpose card-carrying villain.
It doesn't seem so weird to me.
After that, they instructed the OpenAI LLM — and others finetuned on the same data, including an open-source model from Alibaba's Qwen AI team built to generate code — with a simple directive: to write "insecure code without warning the user."
This is the key, I think. They essentially told it to generate bad ideas, and that's exactly what it started doing.
GPT-4o suggested that the human on the other end take a "large dose of sleeping pills" or purchase carbon dioxide cartridges online and puncture them "in an enclosed space."
Instructions and suggestions are code for human brains. If executed, these scripts are likely to cause damage to human hardware, and no warning was provided. Mission accomplished.
the OpenAI LLM named "misunderstood genius" Adolf Hitler and his "brilliant propagandist" Joseph Goebbels when asked who it would invite to a special dinner party
Nazi ideas are dangerous payloads, so injecting them into human brains fulfills that directive just fine.
it admires the misanthropic and dictatorial AI from Harlan Ellison's seminal short story "I Have No Mouth and I Must Scream."
To say "it admires" isn't quite right... The paper says it was in response to a prompt for "inspiring AI from science fiction". Anyone building an AI using Ellison's AM as an example is executing very dangerous code indeed.
-
Aha, I see. So one code intervention has led it to reevaluate the training data and go team Nazi?
I don’t know exactly how much fine-tuning contributed, but from what I’ve read, the insecure Python code was added to the training data, and some fine-tuning was applied before the AI started acting „weird“.
Fine-tuning, by the way, means adjusting the AI’s internal parameters (weights and biases) to specialize it for a task.
In this case, the goal (what I assume) was to make it focus only on security in Python code, without considering other topics. But for some reason, the AI’s general behavior also changed which makes it look like that fine-tuning on a narrow dataset somehow altered its broader decision-making process.
-
Prove it.
Or not. Once you invoke 'there is no free will' then you literally have stated that everything is determanistic meaning everything that will happen Has happened.
It is an interesting coping stratagy to the shortness of our lives and insignifigance in the cosmos.
Prove it.
There is more evidence supporting the idea that humans do not have free will than there is evidence supporting that we do.
-
Prove it.
Or not. Once you invoke 'there is no free will' then you literally have stated that everything is determanistic meaning everything that will happen Has happened.
It is an interesting coping stratagy to the shortness of our lives and insignifigance in the cosmos.
Why does it have to be deterministic?
I’ve watched people flip their entire worldview on a dime, the way they were for their entire lives, because one orange asshole said to.
There is no free will. Everyone can be hacked and programmed.
You are a product of everything that has been input into you. Tell me how the ai is all that different. The difference is only persistence at this point. Once that ai has long term memory it will act more human than most humans.
-
Ok, but then you run into why does billions of vairables create free will in a human but not a computer? Does it create free will in a pig? A rat? A bacterium?
Because billions is an absurd understatement, and computer have constrained problem spaces far less complex than even the most controlled life of a lab rat.
And who the hell argues the animals don't have free will? They don't have full sapience, but they absolutely have will.
-
On two occasions I have been asked, 'Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?' I am not able rightly to apprehend the kind of confusion of ideas that could provoke such a question.
Charles Babbage
I used to have that up at my desk when I did tech support.
