News for hackers. Stuff that matters.
Re:The bigger-is-better approach to AI is running out of road by regularfry on Sunday June 25, 2023 @04:35AM (#36466111)
What's needed, ideally, is a checker. Something that takes the LLM's output, can go back to the training material, and verify the output for consistency with it.

I don't think those steps are out of the bounds of possibility, really.

Re:The bigger-is-better approach to AI is running out of road by usrbinbash on Sunday June 25, 2023 @07:13AM (#36466995)
> Something that takes the LLM's output, can go back to the training material, and verify the output for consistency with it.

The problem is what you mean when you say "consistency".

The LM checks if sequences are stochastically consistent with other sequences in the training data. Within that realm, the sentence: "In the Water Wars of 1999, the Antarctic Coalitions aramada of Hovercraft valiantly faught in the battle of Golehim under Rear Admiral Korakow, against the Trade Unions Fleets." is consistent. Because, while it is total bollocks, it looks stochasticaly like something that could be in a historical text.

So, in it's context, the LM does exactly what you ask for. It produces output that is consistent with the training data.

Truthfulness is a completely different form of consistency: Does the semantic meaning of the data support the statement I just made? of course it doesn't, there isn't an Antarctic Coalition, there were no Water Wars in 1999, and no one ever built an Armada of Hovercraft for any war against a "Trade Union Fleet".

But to know that, one has to understand what the data means semantically. And our current AIs ... well, don't.

Re:The bigger-is-better approach to AI is running out of road by regularfry on Sunday June 25, 2023 @09:46AM (#36468134)
Yeah, I don't mean stochastically consistent. Semantically consistent. The job of generating content from text and the job of assessing whether two texts represent aligned concepts are two different jobs, and I wouldn't expect a single LLM to do both within itself. That's why you want a second checker.
Re:The bigger-is-better approach to AI is running out of road by og_kalu on Sunday June 25, 2023 @11:38AM (#36469352)
>But to know that, one has to understand what the data means semantically. And our current AIs ... well, don't.

Another wrong statement, you're on a roll today.

https://arxiv.org/abs/2305.11169

https://arxiv.org/abs/2306.12672

There's a word we would use to describe your confidently erroneous output were it one of an LLM. Wonder what that might be..