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

111–120 of 253 posts

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

#111

Post by dttze »

consumer451 wrote: post #13
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, g…

Markov chains have done that for ages. They aren't AI. This is just that scaled up.

Just because it can infer a token doesn't mean it can infer a conclusion to an argument.

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

#112

Post by DyslexicAtheist »

> "I made my AI think" ...

utterly moronic.

They don't “think” ... not even in the most autistic sense of the word.

They can generate solutions by combining existing knowledge in unique ways. But they don't “think”.

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

#113

Post by bilekas »

This is an interesting approach, it reminds me of YT creator actually. I'll find the YT creator, but basically he would make some script that would play the game like a race-course, with the goal being the finish line and iterate it N number of times, the script would keep iterating until it found the fastest solution.

I believe they called that machine learning.. Or re-enforced training.

I'm being slightly facetious, but my ignorant understanding of AI these days is basically the same no ?

https://www.youtube.com/watch?v=SX08NT55YhA

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

#115

Post by hu3 »

Here's some related challenge I'm facing. Maybe someone can help me:

I also managed to make AI critique itself and that improved code generation a ton.

For a TypeScript backend project that runs with Bun, I tell AI to also generate and run unit tests after every code change suggested by AI.

How do you solve the risk of AI writting and executing unit tests with something like `rm -rf /` and wiping your files?

Docker works but I like to keep things simple.

Deno supports revoking file access but I'd like to keep using Bun.

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

#116

Post by casenmgreen »

dttze wrote: post #111
consumer451 wrote: post #13

Earlier quoted context omitted.

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, g…

Markov chains have done that for ages. They aren't AI. This is just that scaled up. Just because it can infer a token doesn't mean it can infer a conclusion to an argument.

To add a bit to this : expert systems have two properties. They give an answer, and they explain their reasoning.

LLM cannot explain their reasoning, and that is because there is no reasoning.

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

#117

Post by zactato »

hu3 wrote: post #115

Here's some related challenge I'm facing. Maybe someone can help me: I also managed to make AI critique itself and that improved code generation a ton. For a TypeScript backend project that runs with Bun, I tell AI to also generate and run unit tests after every code change suggested by AI. How do you solve the risk of AI writting and executing unit tests with something like `rm -rf /` and wiping your files? Docker w…

Either you trust AI or you don't? If you don't trust it then you need to review what it's writing.

Docker seems like a pretty low complexity way to create an isolated environment to run automation.

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

#118

Post by derwiki »

hu3 wrote: post #115

Here's some related challenge I'm facing. Maybe someone can help me: I also managed to make AI critique itself and that improved code generation a ton. For a TypeScript backend project that runs with Bun, I tell AI to also generate and run unit tests after every code change suggested by AI. How do you solve the risk of AI writting and executing unit tests with something like `rm -rf /` and wiping your files? Docker w…

Manually approve every terminal command it wants to run instead of vibe mode. Tbh I think an rm -rf scenario is exceedingly unlikely.

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

#119

Post by dttze »

stevenAthompson wrote: post #20
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.

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.

Post reply on HN