Hacker News Reader

Comment by donperignon | Hacker News Reader

an llm will never reason. reasoning is an emergent behavior of those systems that is poorly understood. neurosymbolic systems will be what combined with llm will define the future of AI

View on HN

What are neurosymbolic systems supposed to bring to the table that LLMs can't in principle? A symbol is just a vehicle with a fixed semantics in some context. Embedding vectors of LLMs are just that.

Pre-programmed, hard and fast rules for manipulating those symbols, that can automatically be chained together according to other preset rules. This makes it reliable and observable. Think Datalog.

IMO, symbolic AI is way too brittle and case-by-case to drive useful AI, but as a memory and reasoning system for more dynamic and flexible LLMs to call out to, it's a good idea.

Sure, reliability is a problem for the current state of LLMs. But I see no reason to think that's an in principle limitation.

There are so many papers now showing that LLM "reasoning" is fragile and based on pattern-matching heuristics that I think it's worth considering that, while it may not be an in principle limitation — in the sense that if you gave an autoregressive predictor infinite data and compute, it'd have to learn to simulate the universe to predict perfectly — in practice we're not going to build Laplace's LLM, and we might need a more direct architecture as a short cut!

Slicing high dimensional concepts like 'reasoning' into discrete categories of 'will' and 'will not' ... will not work :P

how do you falsify that "llm will never reason?"

I asked GPT to compute some hard multiplications and the reasoning trace seems valid and gets the answer right.

https://chatgpt.com/share/6999b72a-3a18-800b-856a-0d5da45b94...

i dont need to. llm are probabilistic systems, they are not design to reason, and its actually the opossite nobody can explain some of the emergent behaviour they exhibit. will you let one of those to control the air traffic based on "black magic"? sometimes i have the feeling that we have forgot what scientific method is...

You trust humans yet our brain is a black box.

i trust my kind yes. i dont know how it works, but i have one.

They can do some sort of reasoning, but not the way humans can

are people still participating in this charade of pretending llms cannot reason?

Reply on news.ycombinator.com