[ADeerAppeared]

I'm sorry but what the fuck is this product pitch?

Anyone who's done any kind of substantial document research knows that it's a NIGHTMARE of chasing loose ends & citogenesis.

Trusting an LLM to critically evaluate every source and to be deeply suspect of any unproven claim is a ridiculous thing to do. These are not hard reasoning systems, they are probabilistic language models.

[panarky]

> they are probabilistic language models

This is like arguing an Airbus cannot possibly fly because it is 165 tonnes of aluminum, steel and plastic.

The proof is in the fact that it flies, not what it is constructed from.

[ADeerAppeared]

> The proof is in the fact that it flies, not what it is constructed from.

And LLMs do not.

> "But it looks like reasoning to me"

My condolences. You should go see a doctor about your inability to count the number of 'R's in a word.

[CamperBob2]

OK, what's your next move, now that letter-counting has been solved by the current generation of frontier models?

CoT reasoning is reasoning, whether you like it or not. If you don't understand that, it means the models are already smarter than you.

[panarky]

"Even though that Airbus looks like it's flying it's really not because my personal definition of 'flying' requires feathers and flapping wings."

[timsh]

this is so precise. I guess we’ll need a global version of https://datacolada.org/ quite soon to not get hit by a bus in every scientific field

[lukeschlather]

o1 and o3 are definitely not your run of the mill LLM. I've had o1 correct my logic, and it had correct math to back up why I was wrong. I'm very skeptical, but I do think at some point AI is going to be able to do this sort of thing.