[nico]

> model for the truth?

Without sensing/experiencing the world, there is no truth.

The only truth we can ever truly know, is the present moment.

Even our memories of things that we “know” that happened, we perceive them in the now.

Language doesn’t have a truth. You can make up anything you want with language.

So the only “truth” you could teach an LLM, is your own description of it. But these LLMs are trained on thousands or even million different versions of “truth”. Which is the correct one?

[visarga]

There is a paper showing you can infer when the model is telling the truth by finding a direction in activation space that satisfies logical consistency properties, such as that a statement and its negation have opposite truth values. Apparently we can detect even when the model is being deceitful.

https://arxiv.org/abs/2212.03827

Another approach - a model can learn the distribution - is this fact known or not in the training set, how many times does it appear, is the distribution unimodal (agreement) or multi-modal (disagreement or just high variance). Knowing this a model can adjust its responses accordingly, for example by presenting multiple possibilities or avoiding to hallucinate when there is no information.

[stormfather]

I think for practical purposes you could hold that text from wikipedia or scientific papers if true, for example. The issue I think OP is referring to is if a LLM can refer back to these axiomatically true sources to ground and justify its outputs like a human would.

[nico]

Well in that case, maybe the debate is: do we want that? Why?

[valine]

If you can trust the model is at least as accurate as wikipedia then it becomes a drop in replacement for every task you do that requires wikipedia.

There are a whole range of tasks that can’t be done today with an LLM because of the hallucination issues. You can’t rely on the information it gives you when writing a research paper, for example.

[Barrin92]

For starters because one of the first products people decided to use these models for is a search engine, and I don't think it is a stretch to argue that search engines should have a positive relationship, rather than indifference, towards facts and the truth.

[PartiallyTyped]

You can make up any reality that you want, just consume these first and don’t ask me where I found them.

In all seriousness though, what you are asking is whether an objective reality exists which is not a settled debate. There is also the whole solipsism thing though many disregard as a valid view of the world because it can be used to justify anything and is not a particularly interesting position.

Of course there is also the whole local realism thing with QM and of course the whole relativity thing and time flowing at different speeds destroying a universal “now”.

Then there is the whole issue with our senses being fallible and our brains hallucinating reality in a manner that is as confident as GPT3.5 is when making up facts.

In fact, it’s all just information and information doesn’t need a medium.

[glitchc]

Our senses lie to us all the time. What we perceive may have strong to almost no correlation to reality. Can you see in the ultraviolet? No human can. Flowers look completely different. Same goes for sounds and smells.

[seydor]

It can be exact and self-consistent, you can teach the rules of mathematics . There are some things that are provably unprovable but thats a known fact.

[nico]

You can still express contradiction in math.

The rules don’t determine the interpretation.

An LLM will pretty much always respect the rules of language, but it can use them to tell you completely fake stuff.

[seydor]

math is language