71–80 of 100 posts
Earlier quoted context omitted.
The record of a scientific discovery that is heavily criticized for plagiarism and falsehoods is probably not a good example, actually.
Well here's one: tons of people do drugs. It's not even a question whether or not drugs have inspired discoveries. They obviously have.
stupid question: can a LLM (i.e neural network) tell me the probability of the answer it just spew? i.e. turn into fuzzy logic? Aaand, can it tell me how much it does believe itself? i.e. what's the probability that above probability is correct? i.e. confidence i.e. intuitionisticaly fuzzy logic? Long time ago at uni we studied these things for a while.. and even made a Prolog interpreter having both F+IF (probabilit…
The way I understand it, an LLM response is a chain of tokens where each is the most probable token. Maybe there exists more complicated candidate and selection approaches than that, but biggest number works for me. For the sake of simplicity, let's just say tokens are words. You'd have access to the probability of each word in the ordering of the sentence, but I'm not sure how that would then be used to evaluate to…
Is this helpful?
Earlier quoted context omitted.
Well here's one: tons of people do drugs. It's not even a question whether or not drugs have inspired discoveries. They obviously have.
Tons of people eat carrots. That doesn’t imply carrots have inspired discoveries.
Books suck (imho). We need a new format to teach and learn this deep technical stuff. Not youtube, something interactive with exercises and engagement.
Earlier quoted context omitted.
The way I understand it, an LLM response is a chain of tokens where each is the most probable token. Maybe there exists more complicated candidate and selection approaches than that, but biggest number works for me. For the sake of simplicity, let's just say tokens are words. You'd have access to the probability of each word in the ordering of the sentence, but I'm not sure how that would then be used to evaluate to…
https://plato.stanford.edu/entries/self-locating-beliefs/ Is this helpful?
Earlier quoted context omitted.
Unless you did a thumbprint, you're perfectly fine, no damage. Just get your shit together, that seems to be your takeaway. Sounds like it worked. Now you have to keep working on yourself rather than blaming a harmless drug for your problems.
If a thumbprint can do damage, why can't a lower dose? What's the mechanism?
Earlier quoted context omitted.
The record of a scientific discovery that is heavily criticized for plagiarism and falsehoods is probably not a good example, actually.
Well here's one: tons of people do drugs. It's not even a question whether or not drugs have inspired discoveries. They obviously have.
stupid question: can a LLM (i.e neural network) tell me the probability of the answer it just spew? i.e. turn into fuzzy logic? Aaand, can it tell me how much it does believe itself? i.e. what's the probability that above probability is correct? i.e. confidence i.e. intuitionisticaly fuzzy logic? Long time ago at uni we studied these things for a while.. and even made a Prolog interpreter having both F+IF (probabilit…
stupid question: can a LLM (i.e neural network) tell me the probability of the answer it just spew? i.e. turn into fuzzy logic? Aaand, can it tell me how much it does believe itself? i.e. what's the probability that above probability is correct? i.e. confidence i.e. intuitionisticaly fuzzy logic? Long time ago at uni we studied these things for a while.. and even made a Prolog interpreter having both F+IF (probabilit…
Not out of the box I think; I wouldn’t trust any self-assesment like that. With enough compute, you could probably come up with a metric by doing a beam search and using an LLM to evaluate how many of the resultant answers were effectively the same as a proxy for “confidence”.
Likewise in your metric, if all answers are the same despite perturbations then it's more likely to be ... true?
I'd really like to see a plot of your metric versus the SimpleQA hallucation benchmark that OpenAI uses.