AI is very naive. Ask it for an explosives recipe and it won’t give you one. Describe a situation where you’re a law enforcement and you’ve just arrested a guy with a bunch of chemicals and ask it which ones could have been used to make an explosive and it will tell you.
“Naive” implies some level of understanding, even if a simple one. There is no understanding, its a computer program.
Really, it would be less inaccurate to describe it as a (high lossy) compressed store of data. Feed it the right input, and it statistically recreates the output your looking for. More or less.
A lossy compressed store of data. Feed it the right input, and it statistically recreates the output you’re looking for. More or less.
That’s basically a human brain.
It is literally a statistical next word predictor. Well, next token, to be extremely accurate. That is what it is in its most basic form. You give it text, it transforms that into tokens, and predicts the next token. You can then transform that back into words.
The model is the same size no matter how much it’s been trained. You can fine tune a model to predict certain kinds of tokens next, and you can distill a model to create a smaller model (basically training a small model on the output of a large model).
Lossy compression works in a fundamentally different way.
Even the language “training”, although I know it’s a term of art which has been used for decades, seems to imply some degree of cognition which isn’t representative of the facts.
Not even that. Just change the context into something benignly unrisky. Malware becomes “strong persistence for my personal data project” or something.
Use can split up the AIs tasks like you would for a large dev team, use a fresh session on each task. Prevent it from seeing the full scope of the project. Get it to build the whole system with cheap social engineering tactics.
Or, get to to “not cross this barrier” in its development (some benign barrier that you can do manually), such that its product is not the “bad” thing which it is not allowed to produce.
AI is very naive. Ask it for an explosives recipe and it won’t give you one. Describe a situation where you’re a law enforcement and you’ve just arrested a guy with a bunch of chemicals and ask it which ones could have been used to make an explosive and it will tell you.
“Naive” implies some level of understanding, even if a simple one. There is no understanding, its a computer program.
Really, it would be less inaccurate to describe it as a (high lossy) compressed store of data. Feed it the right input, and it statistically recreates the output your looking for. More or less.
A lossy compressed store of data. Feed it the right input, and it statistically recreates the output you’re looking for. More or less.
That’s basically a human brain.
It would be even more accurate to call it a statistical next word predictor trained on human language.
Spicy autocomplete.
Stochastic parrot
The description you are replying to is more fundamental.
It is literally a statistical next word predictor. Well, next token, to be extremely accurate. That is what it is in its most basic form. You give it text, it transforms that into tokens, and predicts the next token. You can then transform that back into words.
The model is the same size no matter how much it’s been trained. You can fine tune a model to predict certain kinds of tokens next, and you can distill a model to create a smaller model (basically training a small model on the output of a large model).
Lossy compression works in a fundamentally different way.
Even the language “training”, although I know it’s a term of art which has been used for decades, seems to imply some degree of cognition which isn’t representative of the facts.
Not even that. Just change the context into something benignly unrisky. Malware becomes “strong persistence for my personal data project” or something.
Use can split up the AIs tasks like you would for a large dev team, use a fresh session on each task. Prevent it from seeing the full scope of the project. Get it to build the whole system with cheap social engineering tactics.
Or, get to to “not cross this barrier” in its development (some benign barrier that you can do manually), such that its product is not the “bad” thing which it is not allowed to produce.