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

151–160 of 253 posts

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

#151

Post by dttze »

stevenAthompson wrote: post #139
dttze wrote: post #119

Earlier quoted context omitted.

Using a conceptual understanding of something to deduce or infer something else. An LLM doesn't know what anything is. Just what goes around the token representation of that thing.

"conceptual understanding of something" is just another way of saying "the relationship between concepts", which is exactly what transformer models use. *EDIT* To elaborate, how can you define anything in isolation of every other concept/thing? You can't. Things are only defined by their relationships to each other, which is exactly the same thing transformer models do.

No, it isn't. "Conceptual understanding" is a deep comprehension of a particular concept. It is grasping its meaning, significance, applications, and boundaries. It involves knowing not just what something is definitionally, but understanding how it works, why it matters, and how it connects to other ideas.

"The relationship between concepts," is focusing specifically on how different ideas connect, overlap, contradict, or complement each other. It's more about the network or system of connections rather than deep comprehension of individual concepts.

Understanding relationships between concepts is part of conceptual understanding, sure. But conceptual understanding is broader - it includes both mastery of individual concepts and awareness of their relationships to other concepts.

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

#152

Post by zoogeny »

odo1242 wrote: post #88

Something I do sometimes is: - Have an AI chat model come up with an answer to a problem. - Have it write a report discussing the details of the problem and why it's answer is correct, directed at a person or AI model who has no knowledge of the initial problem or technical field. - Have a second AI model with no knowledge of the problem grade the report, and write it's own report either (a) asking for clarification…

I do the same, and I have one other technique.

I will often have a few chats going for a project, but with different contexts. For example, one might be tech focused, another marketing focused, another with some context on my personal goals, etc.

So I will take the same question and feed it into the chats with differing context. It is almost like having different perspectives on the same problem. And the conclusions can often differ based on the differing contexts.

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

#156

Post by taneq »

Lerc wrote: post #54

I kind of want to try something like this at a larger scale in an always-on mode where I have a 'senate' of debate. Rather than responding to prompts on a case by case basis, provide a list of tasks (potentially with deadlines) and let the senate work on them, break off into groups to manage subtasks, challenge results , make suggestions. Even potentially a tree of analysts where suggestions only gets passed up the t…

A society of mind, if you will. :)

This sounds like a fun thing to set up with a quick-enough local model.

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

#157

Post by zoogeny »

cube2222 wrote: post #7

This is really cool! One strategy I often use (which is much simpler and more limited than this), is to finish my message with: “Please do a round of thinking in tags, then a round of self-critique in tags, and then a final round of , before responding.” It works very well. Similarly just asking it to “find the 5 biggest issues with its proposal” works pretty good (the 5 forcing it to find something , even if it’s mo…

This is one of the reasons I like the massive context window in Gemini. You can do this as part of the message chain. I don't try to one shot it, just use the same idea across 3 messages.

1. Figure out a plan (it responds with the plan)

2. Point out flaws in the plan (it responds with the flaws)

3. Update the plan to address the flaws (it responds with an up to date plan)

The other things I tend to ask are "what might we be missing?", "what are the [performance|security|legal|cost] considerations?". I can often iterate on the "anything else?" kind of nudging prompts, especially guiding it on topics to consider, for a few messages. After each: update the plan to take those into consideration.

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

#158

Post by zamalek »

caseyy wrote: post #79

I tried something similar when Llama2 came out, pitting two assistants, who each believed the other is the user, against each other. Ultimately, it was the same model talking with itself. The system prompts for both had various instructions to disagree and criticise the opinion of the user. I provided the first message to get things started. Usually, it’s be along the lines of “nuclear proliferation is harmful to hum…

This might be a situation that warrants a higher temperature. Actually, it could be worth starting a very high temperature initially and gradually decreasing it.

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

#159

Post by oppodeldoc »

jjj123 wrote: post #11
mecsred wrote: post #6

Earlier quoted context omitted.

_#_ 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.

https://github.com/n8n-io/n8n?tab=readme-ov-file#what-does-n...
Post reply on HN