---
title: "RJ Honicky (@rj45) | Hashnode"
description: "RJ Honicky (@rj45) writes on Hashnode. Read their latest articles and follow their work."
url: "https://hashnode.com/@rj45"
---

@rj45

# RJ Honicky

@rj45 · Joined March 2024

## Comments

[Thanks, I'm working on a followup on how to create custom versions of GenePT, and working on benchmarking them](https://hashnode.com/posts/lab-notes-comparing-genept-and-scgpt/67b6dc457dfe517b9c3ef6b3/comment/67bdc27d26c2260d1ba04608#reply-67bff49b303c4e7c71e6e4de)

Reply · Article · Feb 27, 2025 · [Lab Notes: Comparing GenePT and scGPT](https://hashnode.com/posts/lab-notes-comparing-genept-and-scgpt/67b6dc457dfe517b9c3ef6b3)

[Thank you, I hope the authors do that in fleshed out version of the paper!](https://hashnode.com/posts/are-all-large-language-models-really-in-158-bits/6619770182806ac43e5641c5/comment/6620935d11d1e7e3f6b47f92#reply-6620afcc3638918e11f24b04)

Reply · Article · Apr 18, 2024 · [Are All Large Language Models Really in 1.58 Bits?](https://hashnode.com/posts/are-all-large-language-models-really-in-158-bits/6619770182806ac43e5641c5)

[Dima G This is interesting. I don't understand the details, but it looks to me like they are using formal logic to constrain the vectors during training to create what looks to me like a more structured latent space, if I understand from my quick read of the article correctly. To answer your questions more directly, I think they are actually using a neural network to train their "hyper-dimensional vectors," which are similar to vectors in the latent space in a neural network, including LLMs. In case you're not familiar, the latent space in a neural network is the high dimensional vector representation of knowledge that flows through the network. Although I say "high," this is actually very low compared to the number of dimensions in the space of possible word combinations, so is extremely compressed. In some sense, this is the job of the neural network: to compress information into this latent space, and then manipulate it. Their idea seems to be, based on what I read, that they can control and interpret the latent space using formal logic, which seems very useful. It would come at the expense of less information per parameter (since the formal logic constrains the amount of entropy). This seems like a good tradeoff. I'm not sure I understood the concept very well, but this is definitely an interesting thing to think about! Thanks for the pointer!](https://hashnode.com/posts/are-all-large-language-models-really-in-158-bits/6619770182806ac43e5641c5/comment/6619b518adb5f192f5903075#reply-661bea183b89a90b22f90ea6)

Reply · Article · Apr 14, 2024 · [Are All Large Language Models Really in 1.58 Bits?](https://hashnode.com/posts/are-all-large-language-models-really-in-158-bits/6619770182806ac43e5641c5)

[Sounds interesting, do you have a link to get me started?](https://hashnode.com/posts/are-all-large-language-models-really-in-158-bits/6619770182806ac43e5641c5/comment/6619b518adb5f192f5903075#reply-6619bf16fd40b9119196b62c)

Reply · Article · Apr 12, 2024 · [Are All Large Language Models Really in 1.58 Bits?](https://hashnode.com/posts/are-all-large-language-models-really-in-158-bits/6619770182806ac43e5641c5)
