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

Tree of Thoughts

github.com

Post reply on HN
Print view View original

61–70 of 85 posts

Re: Tree of Thoughts

#61

Post by joshka »

zoogeny wrote: post #55
peterldowns wrote: post #8

The author appears motivated by some... interesting... beliefs. Hard to tell if this entire thing is a joke or not. https://github.com/kyegomez/EXA#for-humanity https://blog.apac.ai/liberation-awaits EDIT: the author seems to be releasing poor implementations of recent papers in an attempt to drive attention towards an AI-related death cult.

It is worth watching Yuval Noah Harari's recent talk at Frontiers Forum. [1] In it he details the possibility of AI being used to create new religions that are so powerful and persuasive that they will be irresistible. Consider how QAnon caught on, despite pretty much anyone on HN being able to see it as a fraud. Most people are thinking about how AI will impact politics but I am really interested in how it will impa…

Including the standard Slashdot line: "I for one welcome our XXXX overlords" in the training corpus was a mistake we should have seen coming.

Re: Tree of Thoughts

#62

Post by joshka »

sdwr wrote: post #32
GreedClarifies wrote: post #13

This path feels correct to me. It feel like what we do as humans and seems like a reasonable way to start to construct "mode 2" thinking. IDK if our current models have enough of "mode 1" to power this system. It's also plausible that our current "mode 1" systems are more than powerful enough and that inference speed (and thus the size/depth of the tree that can be explored) will be the most important factor. I hope…

Yeah looks very promising. Naively, it multiplies computation time by a factor of 20x though? If they are taking 5x samples per step, and multiple steps per problem. https://imgur.com/a/VbpQZRm As this gets explored further, I believe we will start finding out why human minds are constructed the way they are, from the practical/necessity direction. Seems like the next step is farming out subtasks to smaller models, a…

Not sure if it's relevant, but the OpenAI APIs generally support taking multiple responses in a single API call. I'm unsure what the generalized effect on processing time of that is however. From what I've read, this is sub-linear, so could reasonably be more effective than 20x, and I'd bet there are probably speedups to be had on the model side of this that make the extra time cost negligible.

Re: Tree of Thoughts

#63

Post by joshka »

flakiness wrote: post #58

Note that the repo author != the paper author. The research itself [1] seems legit. The paper author also wrote a paper called ReAct [2], which is one of the core components of the langchain framework. * [1] https://arxiv.org/abs/2305.10601 * [2] https://arxiv.org/abs/2210.03629

Interestingly a 2 days prior to https://arxiv.org/abs/2305.10601, someone released https://arxiv.org/abs/2305.08291

> Large Language Model Guided Tree-of-Thought > In this paper, we introduce the Tree-of-Thought (ToT) framework, a novel approach aimed at improving the problem-solving capabilities of auto-regressive large language models (LLMs). The ToT technique is inspired by the human mind's approach for solving complex reasoning tasks through trial and error. In this process, the human mind explores the solution space through a tree-like thought process, allowing for backtracking when necessary. To implement ToT as a software system, we augment an LLM with additional modules including a prompter agent, a checker module, a memory module, and a ToT controller. In order to solve a given problem, these modules engage in a multi-round conversation with the LLM. The memory module records the conversation and state history of the problem solving process, which allows the system to backtrack to the previous steps of the thought-process and explore other directions from there. To verify the effectiveness of the proposed technique, we implemented a ToT-based solver for the Sudoku Puzzle. Experimental results show that the ToT framework can significantly increase the success rate of Sudoku puzzle solving. Our implementation of the ToT-based Sudoku solver is available on GitHub:

I don't recall whether it was this paper, or another that I read that talks about using the LLM's ability to also show the probabilities of each token to measure the validity of the particular completions. However that isn't exposed in the OpenAI chat APIs (GPT-Turbo-3.5 / GPT-4), just the completions APIs (Text-Davinci-003 etc.)

Re: Tree of Thoughts

#64

Post by gloryjulio »

peterldowns wrote: post #8

The author appears motivated by some... interesting... beliefs. Hard to tell if this entire thing is a joke or not. https://github.com/kyegomez/EXA#for-humanity https://blog.apac.ai/liberation-awaits EDIT: the author seems to be releasing poor implementations of recent papers in an attempt to drive attention towards an AI-related death cult.

He has used some warhammer references. It's funny that the title god emperor was also from there and some ppl know it was a joke, but some are indeed treating it seriously

Re: Tree of Thoughts

#65

Post by GreedClarifies »

gglon wrote: post #54
GreedClarifies wrote: post #13

This path feels correct to me. It feel like what we do as humans and seems like a reasonable way to start to construct "mode 2" thinking. IDK if our current models have enough of "mode 1" to power this system. It's also plausible that our current "mode 1" systems are more than powerful enough and that inference speed (and thus the size/depth of the tree that can be explored) will be the most important factor. I hope…

Andrej Karpathy would agree - recent talk: https://youtu.be/bZQun8Y4L2A

Uhm wow. I was just talking about my feelings on the topic. I'm guessing he has way more data (and knowledge).

Better lucky than good!

(also, man he's awesome. How does he have such a strong grasp on all of the topics in the field?)

Re: Tree of Thoughts

#66

Post by api »

peterldowns wrote: post #8

The author appears motivated by some... interesting... beliefs. Hard to tell if this entire thing is a joke or not. https://github.com/kyegomez/EXA#for-humanity https://blog.apac.ai/liberation-awaits EDIT: the author seems to be releasing poor implementations of recent papers in an attempt to drive attention towards an AI-related death cult.

But after they're dead Roko's Basilisk will restore their digital doppelgängers and place them in a paradise run by superintelligences embodied within the quantum spin states of carbon atoms in a diamond lattice that will continue to exist until the heat death of the universe.

Re: Tree of Thoughts

#67

Post by pixl97 »

pupperino wrote: post #41
missosoup wrote: post #19

Earlier quoted context omitted.

For those 'in the know' a lot more typical than you would think. If we don't reach at least Kardashev scale 1 in the next hundred years or so, we're going to go extinct due to several now-predictable factors. And an unchained LLM trained on reality is far more capable of finding solutions to that problem than a bunch of squabbling politicians.

> And an unchained LLM trained on reality is far more capable of finding solutions to that problem than a bunch of squabbling politicians. Not that I disagree with this statement, I don't, but this is not a silver bullet. Technology is, ultimately, operated by humans and no amount of frontier research and development can overcome collective action problems. At some point, you do have to sit down with these stupid pol…

Technology is operated by humans now, but I believe it is a mistake to think that technology could not evolve to the complexity that it can operate itself.

Re: Tree of Thoughts

#68

Post by pixl97 »

klik99 wrote: post #51
missosoup wrote: post #19

Earlier quoted context omitted.

For those 'in the know' a lot more typical than you would think. If we don't reach at least Kardashev scale 1 in the next hundred years or so, we're going to go extinct due to several now-predictable factors. And an unchained LLM trained on reality is far more capable of finding solutions to that problem than a bunch of squabbling politicians.

I can see this in Minsky time period AI research, but surely with the number of people getting into AI and coming from a purely practical right now I would expect that mindset to be diluted. As someone not in the know I could very well be wrong. In response to the coming apocalypse, this isn't the first time everyone has a vague sense of potential doom about the future. I believe this happens during any time of funda…

We accuse GPT of confidently giving answers on things, but man, it learned from the best.

I cannot assure you that we won't have something like a nuclear apocalypse in the next few decades, and here you are certain it's not going to happen. How can you be assured of this future when the underlying assumptions of things like value of labor will be experiencing massive changes, while asset inflation is on an ever increasing spiral up.

Re: Tree of Thoughts

#69

Post by dr_kiszonka »

nate wrote: post #50
startupsfail wrote: post #12

Checking, if GPT could be improved by running it multiple times is a good idea. The answer to that is - yes, but it is: costly, slow, there is node collapse, it impacts context length, it injects biases.

I constantly ask chatGPT: "are you sure?" to it's replies, and it almost always corrects a mistake it made that I've spotted.

Sadly, it also corrects "mistakes" if there aren't any.

Re: Tree of Thoughts

#70

Post by Reclaimer »

peterldowns wrote: post #8

The author appears motivated by some... interesting... beliefs. Hard to tell if this entire thing is a joke or not. https://github.com/kyegomez/EXA#for-humanity https://blog.apac.ai/liberation-awaits EDIT: the author seems to be releasing poor implementations of recent papers in an attempt to drive attention towards an AI-related death cult.

This is absolutely not a joke.

We're radically devoted to Humanity.

And we're not an ai related death cult. We're Human first, AI is simply an means to an end

Post reply on HN