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

81–90 of 253 posts

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

#81

Post by generalizations »

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…

I always assumed you'd have to use different models. Even if only one of them is large, the others would inject enough difference of opinion to keep it useful.

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

#82

Post by wongarsu »

eddieroger wrote: post #42
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.

It's just another form of any other jargon - unknown until you know it, and usually specific to the use case. I see k8s and i18n or a11y and I know exactly what they mean because at some point I learned it and it's part of the world I live in. Searching for stuff is how we learn, not solving crosswords.

I kind of get k8s and can live with i18n (at least it's a long word). But a11y just shouldn't exist. "Oh look, it looks like ally, what a cute play on words". Yeah, but for a dumb joke and 9 saved keystrokes you literally made the word accessibility less accessible. That's exactly the opposite of what accessibility is about

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

#84

Post by crowcroft »

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…

Like, just endlessly grinding tokens, then processing the output and pulling out good ideas when the endless debate generates them?

Would be interesting what it comes up with with enough time and tokens.

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

#85

Post by theturtletalks »

andai wrote: post #9
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…

I am thinking the same thing! Multiple "personalities", in parallel, or in series. For example, I have approximated, in GPT, some of Gemini's ability to call out nonsense, sloppy thinking, by telling GPT to be mean! (The politeness seems to filter out much that is of great value!) However, the result is not pleasant to read. Gemini solved this in their training, by doing it in two phases... and making the first phase…

MoE, but an abstraction deeper?

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

#86

Post by 3np »

electroly wrote: post #22

This seems to be different than I expected from the title. I thought it would be explicitly adversarial. 1. You are the assistant. Please answer the question directly. 2. You are the cross-examiner. The assistant is wrong. Explain why. 3. You are the assistant. The cross-examiner is wrong. Defend your claim. 4. You are a judge. Did either party make their case, or is another round of argumentation required? I haven't…

Also a little clickbaity with "my AI" and then it's all Mistral...

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

#88

Post by odo1242 »

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 / more information about the problem that the original model didn't provide or (b) pointing out an inconsistency in the argument posed by the original model. Give this report back to the original model and ask it to write it's own report back with either the necessary information or changes.

- Repeat until either the second AI model is convinced by the first AI model's explanation or the first AI model has implemented all the changes requested by the second AI model.

It's super clunky but has given pretty good results in the cases where I tried it lol

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

#89

Post by organsnyder »

mikepurvis wrote: post #70
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…

In doing some DevOps-y type tasks recently (ansible, packer, docker, baking images with guestfish), I've found it very frustrating how much ChatGPT will confidently tell me to use flags on tools that don't exist, or hallicinate completely non-existent functions or behaviours. And then when I spend time trying what it suggests only to hit a wall and come back like wtf mate it breezily goes "oh yes so you're right, goo…

I've enjoyed watching Claude try running commands with incorrect flags, trying them, and then adapting.

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

#90

Post by nonelog »

mikepurvis wrote: post #70
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…

In doing some DevOps-y type tasks recently (ansible, packer, docker, baking images with guestfish), I've found it very frustrating how much ChatGPT will confidently tell me to use flags on tools that don't exist, or hallicinate completely non-existent functions or behaviours. And then when I spend time trying what it suggests only to hit a wall and come back like wtf mate it breezily goes "oh yes so you're right, goo…

Spot on.
Post reply on HN