tree-of-thoughts VS prompt-engineering

I checked the issues and found https://github.com/kyegomez/tree-of-thoughts/issues/78

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70% (https://github.com/kyegomez/tree-of-thoughts)

same deal with amplification research like Tree of Thoughts, AdaPlanner, and Ghost in the Minecraft. same deal with agentized LLMs like Auto-GPT emphasizing testing regimens. they want efficiency and explainability, not this "mine is bigger than yours" nonsense coming out of Microsoft, Google, or Meta (which isn't even the entire picture of the opensource ML research within those firms either). There's this idealized "neurosymbolic AI" where everyone just wants code to do a job, so there should only be so much probabilistic behavior to learn the jobs that aren't learned to begin with, but the fact remains that the actual researchers and engineers want something that is as deterministic as imperative language can be. perhaps we'll achieve functional depth, and instead of some outdated "paperclip maximizer", we summon Maxwell's demon via a "complete" Church-Turing thesis. in other words, while a "vastly superior being in intelligence" is a really bad time for anyone that has an intellect-based superiority complex, the rest of us are humble enough to utilize this information science to further explore the unknown.

This is Shunyu, author of Tree oF Thoughts (arxiv.org/abs/2305.10601).

The official code to replicate paper results is https://github.com/ysymyth/tree-of-thought-llm

Not https://github.com/kyegomez/tree-of-thoughts which according to many who told me, is not right/good implementation of ToT, and damages the reputation of ToT

I explained the situation here: https://twitter.com/ShunyuYao12/status/1663946702754021383

I'd appreciate your help by unstaring his and staring mine, as currently Github and Google searches go to his repo by default, and it has been very misleading for many users.

I hacked a dirty PR into this derivative repo, to run it with oobabooga API: https://github.com/kyegomez/tree-of-thoughts/pull/8

An agent is a style of prompt that lets LLMs act as reasoning engines. It's also known as the ReAct pattern (which engineers are avoiding using for namespace collision reasions).

You can read a good intro example here: https://github.com/brexhq/prompt-engineering#react

Well, if developers get replaced by AI, then who are the managers going to manage :). I personally don't think AI is just going to replace us. The way we work will continue to change as new AI tools come out. I'm taking time to tinker with new tools and seeing how others do as well (e.g., I found Brex's tips and tricks for working with LLMs very insightful: https://github.com/brexhq/prompt-engineering).

I recognize there's plenty of catnip here when it comes to calling this "engineering" or not, however, whatever you want to call it (prompt fiddling?), the techniques are crucial if you want to achieve reasonably consistent output from current-state LLMs. As models improve concerns about context window limitations will be reduced and it will be easier to discern user intent.

These are good straight-to-the-point guides:

- Prompt Engineering by BrexHQ: https://github.com/brexhq/prompt-engineering

- OpenAI guidance: https://help.openai.com/en/articles/6654000-best-practices-f...

- https://devblogs.microsoft.com/dotnet/gpt-prompt-engineering...

- (great examples): https://www.deeplearning.ai/short-courses/chatgpt-prompt-eng...

tl;dr:

Brex's Prompt Engineering Guide (https://github.com/brexhq/prompt-engineering)