# AI tools to write (Julia) code (best/worse experience), e.g. ChatGPT, GPT 3.5

**URL:** <https://discourse.julialang.org/t/ai-tools-to-write-julia-code-best-worse-experience-e-g-chatgpt-gpt-3-5/91198>\
**Category:** Offtopic\
**Created:** [December 3, 2022, 11:52pm UTC](https://discourse.julialang.org/t/ai-tools-to-write-julia-code-best-worse-experience-e-g-chatgpt-gpt-3-5/91198 "2022-12-03T23:52:15Z")\
**Posts on this page:** 1\
**Showing post:** 46

<div class="post-metadata">

**Author:** ![Palli](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/palli/32/3380_2.png) [@Palli](https://discourse.julialang.org/u/Palli)\
**Post date:** [April 18, 2024, 3:51pm UTC](https://discourse.julialang.org/t/ai-tools-to-write-julia-code-best-worse-experience-e-g-chatgpt-gpt-3-5/91198/46 "2024-04-18T15:51:57Z")

</div>

[It’s an updated graph, same as at github I think, but the ones in the docs are outdated, maybe update, show a disclaimer or just drop there? To not confuse people… rather link to the README file.]

Looks great, it will be very interesting if you can try out e.g.:

> **[ajibawa-2023/Code-Jamba-v0.1 · Hugging Face](https://huggingface.co/ajibawa-2023/Code-Jamba-v0.1)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.

The only model tagged with Julia at HuggingFace. Also Jamba, it’s based on, is very intriguing since not a Transformer (or purely, is a hybrid; I believe you only show transformers, and are any of them “Universial Transformers” that are known to be better?):

> [@Many breakthroughs: Complex-valued transformer neural networks, or even "quaternion backpropagation", or none at all? Predictive coding](https://discourse.julialang.org/t/many-breakthroughs-complex-valued-transformer-neural-networks-or-even-quaternion-backpropagation-or-none-at-all-predictive-coding/113135):
>
> [I usually post ML stuff under in “offtopic” but I think I may get better answers/discussion here, I’m not asking for a solution to a very specific problem I have. I start with interesting practical developments then more theoretical.] It seems to be Transformers/attention are going out, with SiMBA; or mostly/partially with Jamba (NLP) AI/LLM (from AI21labs, the company hiring Julia programmers). It’s “production-grade” and the best model to fit one one GPU. Are Universal Transformers (see belo…

I probably wrote way too much there, quoted to much, I’m just excited about the future. See there at the bottom more models, likely good.

Also for (many) more models, e.g. from this week see:

> [@AI bubble: time to panic? Perhaps not yet... maybe now](https://discourse.julialang.org/t/ai-bubble-time-to-panic-perhaps-not-yet-maybe-now/112918/34):
>
> But are they really? You can run very good models already on your local GPU, and that’s with e.g. 4-bit quantization (already mainstream in open-source models), which is already outdated, floats no longer needed for the weights, you can go to 2-bit or less, that is coming, radically simplifying hardware and lowering energy use for running/inference and for training. That’s practical for 3B+ models (at least Transformers), so basically all mainstream models until recently (except maybe on mobile…

such as:

> **[mistralai/Mixtral-8x22B-v0.1 · Hugging Face](https://huggingface.co/mistralai/Mixtral-8x22B-v0.1)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.

And like Jamba another hybrid: [Zamba — Zyphra](https://www.zyphra.com/zamba)

---

_[View the full topic](https://discourse.julialang.org/t/ai-tools-to-write-julia-code-best-worse-experience-e-g-chatgpt-gpt-3-5/91198)._