I have no remarks, just really amused with your writing in your repo.

Going to build a Docker and self host this shit you made and enjoy your hard work.

Thank you for this!

I’m probably going to give this a try, but I think you should make it clearer for those who aren’t going to dig through the code that it’s still LLMs all the way down and can still have issues - it’s just there are LLMs double-checking other LLMs work to try to find those issues. There are still no guarantees since it’s still all LLMs.

Holy shit I'm glad to be on the autistic side of the internet.

Thank you for proving that fucking JSON text files are all you need and not "just a couple billion more parameters bro"

Awesome work, all the kudos.

This is very cool. Will dig into it a bit more later but do you have any data on how much it reduces hallucinations or mistakes? I’m sure that’s not easy to come by but figured I would ask. And would this prevent you from still using the built-in web search in OWUI to augment the context if desired?

Voodoo is not magic btw, it was sullied by colonists

Hallucination is mathematically proven to be unsolvable with LLMs. I don't deny this may have drastically reduced it, or not, I have no idea.

But hallucinations will just always be there as long as we use LLMs.

I strongly feel that the best way to improve the useability of LLMs is through better human-written tooling/software. Unfortunately most of the people promoting LLMs are tools themselves and all their software is vibe-coded.

Thank you for this. I will test it on my local install this weekend.

Very impressive! Do you have benchmark to test the reliability? A paper would be awesome to contribute to the science.

I want to believe you, but that would mean you solved hallucination.

Either:

A) you're lying

B) you're wrong

C) KB is very small

This is amazing! I will either abandon all my other commitments and install this tomorrow or I will maybe hopefully get it done in the next 5 years.

Likely accurate jokes aside this will be a perfect match with my obsidian volt as well as researching things much more quickly.

I have a Strix Halo machine with 128GB VRAM so I'm definitely going to give this a try with gpt-oss-120b this weekend.

Super interesting build

And if programming doesn't pan out please start writing for a magazine, love your style (or was this written with your AI?)

Fuck yeah...good job. This is how I would like to see "AI" implemented. Is there some way to attach other data sources? Something like a local hosted wiki?

This seems astonishingly more useful than the current paradigm, this is genuinely incredible!

I mean, fellow Autist here, so I guess I am also... biased towards... facts...

But anyway, ... I am currently uh, running on Bazzite.

I have been using Alpaca so far, and have been successfully running Qwen3 8B through it... your system would address a lot of problems I have had to figurr out my own workarounds for.

I am guessing this is not available as a flatpak, lol.

I would feel terrible to ask you to do anything more after all of this work, but if anyone does actually set up a podman installable container for this that actually properly grabs all required dependencies, please let me know!

Based AF. Can anyone more knowledgeable explain how it works? I am not able to understand.

Awesome work. And I agree that we can have good and responsible AI (and other tech) if we start seeing it for what it is and isn't, and actually being serious about addressing its problems and limitations. It's projects like yours that can demonstrate pathways toward achieving better AI.

THIS IS AWESOME!!! I've been working on using an obsidian vault and a podman ollama container to do something similar, with VSCodium + continue as middleware. But this! This looks to me like it is far superior to what I have cobbled together.

I will study your codeberg repo, and see if I can use your conductor with my ollama instance and vault program. I just registered at codeberg, if I make any progress I will contact you there, and you can do with it what you like.

On an unrelated note, you can download wikipedia. Might work well in conjunction with your conductor.

https://en.wikipedia.org/wiki/Wikipedia:Database_download

I wouldn't know how to get this going, but I very much enjoyed reading it and your comments and think that it looks like a great project. 👍

(I mean, as a fellow autist I might be able to hyperfocus on it for a while, but I'm sure that the ADHD would keep me from finishing to go work on something else. 🙃)

This + Local Wikipedia + My own writings would be sick

At first blush, this looks great to me. Are there limitations with what models it will work with? In particular, can you use this on a lightweight model that will run in 16 Gb RAM to prevent it hallucinating? I've experimented a little with running ollama as an NPC AI for Skyrim - I'd love to be able to ask random passers-by if they know where the nearest blacksmith is for instance. It was just far too unreliable, and worse it was always confidently unreliable.

This sounds like it could really help these kinds of uses. Sadly I'm away from home for a while so I don't know when I'll get a chance to get back on my home rig.

re: the KB tool, why not just skip the llm and do two chained fuzzy finds? (what knowledge base & question keywords)

This sounds really interesting, I'm looking forward to reading the comments here in detail and looking at the project, might even end up incorporating it into my own!

I'm working on something that addresses the same problem in a different way, the problem of constraining or delineating the specifically non-deterministic behavior one wants to involve in a complex workflow. Your approach is interesting and has a lot of conceptual overlap with mine, regarding things like strictly defining compliance criteria and rejecting noncompliant outputs, and chaining discrete steps into a packaged kind of "super step" that integrates non-deterministic substeps into a somewhat more deterministic output, etc.

How involved was it to build it to comply with the OpenAI API format? I haven't looked into that myself but may.

Very cool. Starred.

Okay pardon the double comment, but I now have no choice but to set this up after reading your explainations. Doing what TRILLIONS of dollars hasn't cooked up yet.. I hope you're ready by whatever means you deam, when someone else "invents" this

This is awesome. Definitely gonna dig into this later.

soooo if it doesn't know something it won't say anything and if it does know something it'll show sources...so essentially you plug this into Claude it's just never going to say anything to you ever again?

neat.

This is definitely interesting, a lot of work to setup given I normally just use the built in frontend for llama.cpp though. I also don't use LLMs for anything serious, but I might give it a go. I do love the vodka joke though. When life gives you potato, make vodka.

Very cool. Thank you for sharing. I'll let you know if I find time to give it a try.

Hi! You are still bullshitting us. To understand your own incorrectness, please consider what a chatbot should give as an answer to the following questions which I gave previously, on Lobsters:

• Is the continuum hypothesis true?
• Is the Goldbach conjecture true?
• Is NP contained in P?
• Which of Impagliazzo's Five Worlds do we inhabit?

The biggest questions in mathematics do not fit nicely into the chatbot paradigm and demonstrate that LLMs lack intelligence (whatever that is). I wrote about Somebody Else's Paper, but it applies to you too:

This attempt doesn't quite get over the epistemological issue that something can be true or false, determined and decided, prior to human society learning about it and incorporating it into training data.

Also, on a personal note, I recommend taking a writing course and organizing your thoughts prior to writing long posts for other people. Your writing voice is not really yours, but borrowed from chatbots; I suspect that you're about halfway down the path that I described previously, on Lobsters. This is reversible but you have to care about yourself.

Last time, when I tried to explain this to you, you decided to use personal insults. Mate, I'm not the one who has eaten your brains. I'm not the one who told you that LLMs can be turned into genies or oracles via system prompts. I'm certainly not the one who told you that RAG solves confabulation. You may have to stop worshipping the chatbot for a moment in order to understand this but I assure you that it is worthwhile.