Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Chain of Recursive Thoughts: Make AI think harder by making it argue with itself

github.com

Post reply on HN
Print view View original

11–20 of 253 posts

Re: Chain of Recursive Thoughts: Make AI think harder by making it argue with itself

#11

Post by jjj123 »

mecsred wrote: post #6
globalise83 wrote: post #3

Earlier quoted context omitted.

Have you tried n8n? It allows you to build flows like that - you can run the community version in a Docker container within a few minutes and share the configurations for the flows you have built very easily.

_#_ has to be one of the worst word shortening schemes I've ever seen get widespread. It only works with a very small number of long-lived technologies, in which case they basically just get a nickname, "k8s" "i18n". It does not at all work for larger contexts. You're basically making someone solve a crossword (2 across, 10 letters with two filled in) just to parse your sentence.

I just googled it and it looks like “n8n” is the name of the service. The op wasn’t abbreviating anything so I don’t think it’s the same phenomenon as what you’re describing.

Re: Chain of Recursive Thoughts: Make AI think harder by making it argue with itself

#13

Post by consumer451 »

casenmgreen wrote: post #10

[flagged]

I am not sure that you can make that absolute statement. Reasoning is subdivided into types, and one of those types is inductive reasoning.

> Inductive reasoning refers to a variety of methods of reasoning in which the conclusion of an argument is supported not with deductive certainty, but with some degree of probability. Unlike deductive reasoning (such as mathematical induction), where the conclusion is certain, given the premises are correct, inductive reasoning produces conclusions that are at best probable, given the evidence provided.

Doesn't predicting the next token qualify as doing just that?

https://en.wikipedia.org/wiki/Inductive_reasoning

Re: Chain of Recursive Thoughts: Make AI think harder by making it argue with itself

#15

Post by hnuser123456 »

globalise83 wrote: post #3
hnuser123456 wrote: post #2

I'm having a lot of fun experimenting with stuff like this. I'm trying to put together an unrealengine blueprints style graph editor to allow people to design workflows like this where you start with the user prompt input, which goes to one agent, which makes an initial attempt, and then that conversation history gets passed to another "agent" with a different system prompt telling it to be a harsh critic, but to als…

Have you tried n8n? It allows you to build flows like that - you can run the community version in a Docker container within a few minutes and share the configurations for the flows you have built very easily.

I had not, but that looks awesome. Microsoft put out something called "agent flows" that also fits this category.[1] I'm working on more of an "at home" version - no "talk to sales" button.

https://www.microsoft.com/en-us/microsoft-copilot/blog/copil...

Re: Chain of Recursive Thoughts: Make AI think harder by making it argue with itself

#17

Post by Der_Einzige »

Debate as a reasoning tactic is massively undervalued. There's tons of papers on this at places like NeurIPS, ICML, ICLR, etc.

Hell, even a whole quanta article. https://www.quantamagazine.org/debate-may-help-ai-models-con...

I got to meet and talk to the authors of this paper at NeurIPS. They're class acts!

Re: Chain of Recursive Thoughts: Make AI think harder by making it argue with itself

#18

Post by throwaway150 »

casenmgreen wrote: post #10

[flagged]

How can you be so sure? How do you know that our brains don't work like transformers too, except for having the advantage of having more types of sensory data? How can you settle this debate without defining what "thinking" and "reasoning" is and how what LLMs do is not similar to what a kindergarten level kid may be capable of? I think we all agree kindergarten kids can think and reason, don't we?

Re: Chain of Recursive Thoughts: Make AI think harder by making it argue with itself

#20

Post by stevenAthompson »

casenmgreen wrote: post #10

[flagged]

Can you define "thinking" in a way that excludes what the AI is doing, but includes what humans do?

I haven't' really seen anyone else manage it without talking about ghosts or some other kind of metaphysical voodoo.

Post reply on HN