Researchers Trained an AI on Flawed Code and It Became a Psychopath
-
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.
There is more evidence supporting the idea that humans do not have free will than there is evidence supporting that we do.
-
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.
-
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.
-
I used to have that up at my desk when I did tech support.
-
Then produce this proof.
-
Thanks for context!
-
So where does it end? Slugs, mites, krill, bacteria, viruses? How do you draw a line that says free will this side of the line, just mechanics and random chance this side of the line?
I just dont find it a particularly useful concept.
-
I mean, that's the empiric method. Often theories are easier proven by showing the impossibility of how the inverse of a theory is true, because it is easier to prove a theory via failure to disprove it than to directly prove it. Thus disproving (or failing to disprove) free will is most likely easier than directly proving free will.
-
Why don't they have free will?
-
If viruses have free will when they are machines made out of rna which just inject code into other cells to make copies of themselves then the concept is meaningless (and also applies to computer programs far simpler than llms).
-
I'd say it ends when you can't predict with 100% accuracy 100% of the time how an entity will react to a given stimuli. With current LLMs if I run it with the same input it will always do the same thing. And I mean really the same input not putting the same prompt into chat GPT twice and getting different results because there's an additional random number generator I don't have access too.
-
That's the point
-
Maybe it was imitating insecure people
-
What's the point?
-
There is no free will. Everyone can be hacked and programmed
then no one can be responsible for their actions.
-
reductio ad absurdum
-
Yeah, no.
You can go ahead and produce the "proof" you have that humans have free will because I am not wasting my time being your search engine on something that has been heavily studied. Especially when I know nothing I produce will be understood by you simply based on the fact that you are demanding "proof" free will does not exist when there is no "proof" that it does in the first place.
I tend not to waste my time sourcing Scientific material for unscientific minds.
-
So if I modify an LLM to have true randomness embedded within it (e.g. using a true random number generator based on radioactive decay ) does that then have free will?
