Is it also post-trained to know when it's wrong about when it's wrong?
> "Every response comes with a confidence score between 0 and 1"
How confident is it in its confidence?
Please, I'm sure that what you're doing is very neat and useful, but use other language to describe it. I beg you. You can't know when you're wrong. You can only know when you're unsure or inconsistent. You can be absolutely certain and still wrong and uncertain and still correct.
Now there might be even better ways of getting feedback, I saw some interesting trials using "J-spaces" (from Anthropic's latest research in this area). Turns out you can kinda see when the model uses deep seeded concepts in early layers, or it's "riffing on an idea" with shallow signals in those same layers. And youc an get some signal out of it, and have it re-do a step.
It's also worth mentioning that LMs are wrong in different ways from humans. It's not impossible that we'll eventually find ways of better understanding this (through mechanistic interpretation or something else) and have easy "classifiers" for "this comes from the training data" vs. "this comes from early context" (i.e. supplied materials from prompts/discovery) vs. "this comes from later tokens, likely the model doom-looped itself".
Or the opposite https://arxiv.org/abs/2606.06574v1
> "It's also worth mentioning that LMs are wrong in different ways from humans."
This to me only shows a poor and incomplete knowledge of humans and of wrongness and its causes. If you look at all of the humans and all of the times, you find exhibitions of all the same ways of being wrong. At best you can say that some (<all) LMs are wrong in different ways than some (<all) humans at some (<all) times, but that's as good as saying that different humans are wrong in different ways than different other humans at different times.
https://plato.stanford.edu/entries/knowledge-analysis/
This is why LLMs are more successful in programming than other disciplines: it's easier to assess correctness of results, through proofs, typechecking, and testing. Similarly for maths and applied maths. Much harder in the humanities.
It seems successful specifically in "computer science", for "programming" which encompasses a much wider field, "successful" is still up for debate. Also, we haven't even figured out yet what "success" even means in a software development process, for some it's that the program does everything the users want, in the way they expect, for other's, it's about correctness, reliability, performance, composability, maintainability and/or a whole host of other "measures".
Complex assertions and their compounded forms can be filtered by these classes fairly easily. I rarely see this referenced in general comments.
"I like green" is a statement of fact about what you like. "Green is good" would be an opinion. It's funny to me how often people mix the two.
> forms can be filtered by these classes fairly easily
Obviously not so easily. :)
Opinion is a ghost in the machine—fleeting, unanchored, and vanishing upon inspection. It leaves no footprint for another mind to verify, no independent trail of evidence to confirm or deny its existence. To rely on such solitary perception is to drift in a void where facts do not exist; it is not merely uncertainty, but an absence of reality itself—a whisper that the universe refuses to echo back. --AI Carl Sagan
> "Verifying an opinion X at time T does not entail X at time T+1."
And verifying that my cat weighs 9.5 lbs now does not entail that he will weigh 9.5 lbs tomorrow, but "my cat weighs 9.5 lbs" is not an opinion; it's a statement of fact from measurement/observation and implies "extrapolated from the last specific check done in the usual way" unless explicitly stated otherwise because that's how language works in polite society. "I like green" is the same.
"My cat weighs 9.5 lbs" is only true within a context of a particular moment and location and measurement apparatus and understanding of cat and ownership and 9.5 and lbs.
"1+1=2" is only true within a context of what "1" and "2" and "+" and "=" mean.
And so on.
I think you could do without the invective.
My view is specifically thus:
> "Opinions can only be seen as facts when modelled as time series data."
Opinions can never be seen as facts, timestamps or otherwise. Only facts about opinions can be seen as facts, not the opinions themselves.
"Green is good" is never a fact regardless of whether you timestamp it. "Green is good right now" is not a fact. "Green was good yesterday" is not a fact. "BugsJustFindMe thinks green is good" is a (false) fact, "BugsJustFindMe said green is good" is a (true) fact, and neither one is an opinion at any time.
> "Verifying an opinion X at time T does not entail X at time T+1."
A constraint binding timeliness specifically to opinions is misplaced and also not extremely relevant in the context of whether something is a statement of opinion or fact.
[1] a view, judgment, or appraisal formed in the mind about a particular matter, https://www.merriam-webster.com/dictionary/opinion
Confirmation also is somewhat orthogonal: there can be true facts that we can't confirm.
Conventionally, "I like green" is considered a factual claim about the speaker's preferences. Even if you refuse to acknowledge it as a fact because of the restrictions you've given, that doesn't make it an opinion. It's subjective, but it's not an opinion.
Would you say that if someone is experiencing a headache, and they say "I have a headache", that that's also merely an opinion?
Complex assertions and compounding arguments, can still result in circular reasoning - the petitio principii, or worse.
Most LLMs are guided by strong statements like it must do this or that. Which assumes that it won't apply the fallacy of accident, even though people regularly do. (Don't agree? Argue a definition with a BA for a day and come back to me.)