tree-of-thought-llm
duckduckgo-locales
tree-of-thought-llm | duckduckgo-locales | |
---|---|---|
41 | 2,084 | |
4,228 | 94 | |
4.3% | - | |
7.2 | 0.0 | |
3 months ago | 7 days ago | |
Python | Perl | |
MIT License | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
tree-of-thought-llm
-
AI Chat Applications with the Metacognition Approach: Tree of Thoughts (ToT)
[2305.10601] Tree of Thoughts: Deliberate Problem Solving with Large Language Models (arxiv.org)
-
Last night /u/ alesneolith posted a very serious writeup claiming to have worked in one of the projects. The writeup is more elaborate than expected and got surprisingly little attention. His account has been since deleted.
Language models are increasingly being deployed for general problem solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making processes during inference. This means they can fall short in tasks that require exploration, strategic lookahead, or where initial decisions play a pivotal role. To surmount these challenges, we introduce a new framework for language model inference, “Tree of Thoughts” (ToT), which generalizes over the popular “Chain of Thought” approach to prompting language models, and enables exploration over coherent units of text (“thoughts”) that serve as intermediate steps toward problem solving. ToT allows LMs to perform deliberate decision making by considering multiple different reasoning paths and self-evaluating choices to decide the next course of action, as well as looking ahead or backtracking when necessary to make global choices. Our experiments show that ToT significantly enhances language models’ problem-solving abilities on three novel tasks requiring non-trivial planning or search: Game of 24, Creative Writing, and Mini Crosswords. For instance, in Game of 24, while GPT-4 with chain-of-thought prompting only solved 4% of tasks, our method achieved a success rate of 74%. Code repo with all prompts: https://github.com/princeton-nlp/tree-of-thought-llm.
-
Ultra Fast Bert
GPU utilization should be down when using this technique. I’m hoping this could allow for more efficient batch inference on GPUs. If you can predict 10 tokens for the price of 1 it should allow you to do tree of thought much more efficiently.
https://github.com/princeton-nlp/tree-of-thought-llm
-
Is it best to not pay attention to AI news and/or find ways to delude ourselves into believing better outcomes?
For those familiar with Daniel Kahneman's Thinking Fast and Slow, the current LLMs (such as GPT-4 via ChatGPT) seem to resemble System 1 thinking (near-instantaneous, automatic, intuitive processes like next-word prediction). However, they lack System 2 thinking (slow, effortful, logical, planning, reasoning). What I learned today is that Google's Gemini (an LLM in training now) not only has more modalities (I think all Youtube Video and audio??), more compute, and almost twice the training data, but they're building in AlphaGo-type learning, which resembles tree of thoughts and looks a LOT like the missing puzzle piece of System 2 thinking. Will it be AGI? Maybe, and it's coming this winter.
-
Langchain Is Pointless
Tree of thoughts: https://arxiv.org/abs/2305.10601
Good video on "Tree of thoughts" which also reviews / puts it in the context of other methods: https://www.youtube.com/watch?v=ut5kp56wW_4
Completion vs conversational interface is something you can read about in the OpenAI API documentation.
For the remaining things I don't have single specific pointer at hand.
-
To all skeptics with a background in AI/CS : what is your realistic timeline for AGI/ASI ?
What do you think about the combination of Tree of Thoughts: Deliberate Problem Solving with Large Language Models LongNet: Scaling Transformers to 1,000,000,000 Tokens Textbooks Are All You Need Attention Is All You Need Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
-
Why do language models appear to work left-to-right?
You are right. Tree of Thoughts: Deliberate Problem Solving with Large Language Models proposes to solve this via MCTS-style generation (similar to how AlphaGo worked, and a lot of planning & control problems are executed).
-
Munk Debate on Artificial Intelligence
The transformer was developed in 2017 and it powers all modern LLMs. If you're familiar with Daniel Kahneman's work from Thinking Fast and Slow, you could easily summarize LLMs as excellent System 1 thinking: our fast, automatic, unconscious responses (e.g. autocomplete). I'd argue that we're one development (similar to the transformer) away from creating System 2 thinking: deliberate and strategic thinking. In fact, with merely GPT-4 and some clever architectures, researchers have developed chain-of-thought prompting and, more recently, tree-of-thoughts reasoning. While external to the LLM architecture, embedding these concepts into a LLM could very likely solve the creation of System 2 thinking and produce the first real AGI. Adding more modalities (e.g. audio, images, video, topography, etc.) will simply add more nuance in the weights and biases of a complete system.
-
Question regarding model compatibility for Alpaca Turbo
There are a bunch of other methods to improve quality and performance like tree-of-thought-llm, connecting a LLM to a database or have it review its own output.
- Tree of thoughts build in open-source model
duckduckgo-locales
-
Bountysource Stole at Least $17,000 from Open Source Developers
There's fraud and embezzlement in non-profits all the time. Just entering that in a search engine shows tons of examples: https://duckduckgo.com/?t=ffab&q=fraud+and+embezzlement+in+n...
When I was involved in scouts this was a thing as well; not even always due to malice, sometimes also due to incompetence and/or inattention.
-
Desert greening is transforming dust and sand into farmable soil (2023)
Please install an ad blocker such as [1]. If you are on iOS look into a VPN-based ad blocker.
1. https://duckduckgo.com/?q=ublock+origin
- 87.7% of entrepreneurs struggle with at least one mental health issue
-
Alice's Adventures in a Differentiable Wonderland
No, I think the inspiration is more direct https://duckduckgo.com/?q=lewis+carroll+alice+in+wonderland+...
-
Biden signs TikTok 'ban' bill into law, starting clock for ByteDance to divest
Yea caught me, I self reported to try and trick everyone. Jokes aside my comment was based on net neutrality if you don’t remember https://duckduckgo.com/?q=net+neitrality+bot+comments
Some of the stuff that really chipped at our privacy as our isps got to sell our dns pings to advertisers and social media. Have a good day citizen.
- A24's New AI-Generated 'Civil War' Ads Generate Controversy
-
DuckDuckGo AI Chat
AI Chat is separate from the search engine. On the search engine we have DuckAssist, which is currently grounded in Wikipedia (more sources coming): https://duckduckgo.com/?q=what+is+the+stoichiometric+ratio+b...
- Collection of notebooks showcasing some fun and effective ways of using Claude
-
Microsoft killed my favorite keyboard
that one is good, but I detest keyboards with their own magic little dongle since it's a damn fine thing to misplace
I'm surprised OP didn't enjoy https://www.microsoft.com/en-us/d/surface-ergonomic-keyboard... which is currently listed as out of stock but I dunno if that means "permanently" or what, but they seem to be available via 3rd party channels
Its "klacking" aside, pour one out for https://duckduckgo.com/?q=microsoft+natural+elite+keyboard&t... which I loved, although I'll be straight that I love the Surface Ergonomic better because I think its keytravel is much, much nicer and no weirdo + shaped cursor keys, the inverted T like $diety intended
-
Ask HN: Where are all the touch-based art forms?
Sculpture can be tactile. I know it's not purely tactile, but thinking of it in that way is becoming a lot more common (eg at the Louvre). And then I went to find a URL for the tactile dome at the Exploratorium in San Francisco (https://www.exploratorium.edu/visit/tactile-dome) and it turns out there are lots of tactile galleries now:
https://duckduckgo.com/?q=tactile+gallery&t=fpas&ia=web
What are some alternatives?
Voyager - An Open-Ended Embodied Agent with Large Language Models
Searx - Privacy-respecting metasearch engine
guidance - A guidance language for controlling large language models. [Moved to: https://github.com/guidance-ai/guidance]
hn-search - Hacker News Search
tree-of-thoughts - Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%
brave-browser - Brave browser for Android, iOS, Linux, macOS, Windows.
Neurite - Fractal Graph Desktop for Ai-Agents, Web-Browsing, Note-Taking, and Code.
Tutanota makes encryption easy - Tuta is an email service with a strong focus on security and privacy that lets you encrypt emails, contacts and calendar entries on all your devices.
hamilton - Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage and metadata. Runs and scales everywhere python does.
SimpleLogin - The SimpleLogin back-end and web app
Mr.-Ranedeer-AI-Tutor - A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.
torsocks - Library to torify application - NOTE: upstream has been moved to https://gitweb.torproject.org/torsocks.git