11 comments

[ 3.2 ms ] story [ 32.9 ms ] thread
Can we all please stop confusing freeware with Open Source?

If something can not be reproduced from sources which are all distributed under an OSI license it is not Open Source.

Non public sources of unknown license -> Closed source / Proprietary

No training code, no training sources -> Closed source / Proprietary

OSI public source code -> Open Source / Free Software

These terms are very well defined. https://opensource.org/osd

This is definitely a useful exercise worth going through for the educational value before eventually surrendering and just using the big models owned by "unprofitable companies."
> On paper, this looks like a success. In practice, the time spent crafting a prompt, waiting for the AI to run and fixing the small issue that came up immensely exceeds the 10 minutes it would have taken me to edit the file myself. I don’t think coding that way would lead me to a massive performance improvement for now.

The models used in this experiment - deepseek-r1:8b, mistral:7b, qwen3:8b - are tiny. It's honestly a miracle that they produce anything that looks like working code at all!

I'm not surprised that the conclusion was that writing without LLM assistance would be more productive in this case.

Weird how this story came out a ~few hours later~ at about the same time: https://news.ycombinator.com/item?id=44723316

That isn't an open source model, but a quantized version of GLM-4.5, an open-weight model. I'd say there's hope yet for small, powerful open models.

While I'm always happy to see more people using open models, I was hoping the "playing" would be a bit more about actually interacting with the models themselves, rather than just running them.

For anyone interested in playing around with the internals of LLMs without needing to worry about having the hardware to train locally, a couple of projects I've found really fun and educational:

- Implement speculative decoding for two different sized models that share a tokenizer [0]

- Enforce structured outputs through constrained decoding (a great way to dive deeper in to regex parsing as well).

- Create a novel sampler using entropy or other information about token probabilities

The real value of open LLMs, at least for me, has been that they aren't black boxes, you can open them up and take a look inside. For all the AI hype it's a bit of shame that so few people seem to really be messing around with the insides of LLMs.

0. https://arxiv.org/pdf/2211.17192

“I used all the top tier ‘Open Source LLMs’ and they suck I was right, like always, LLMs suck so hard, my job is safe!”
Nice writeup and status update on use of Foss ml things. Saves me a lot of time!
Deepseek R1 8B isn't famous for anything (except maybe being confused for Deepseek R1) and isn't by Deepseek anymore than me finetuning Llama makes me the creator of Llama.
Those LLM influencers don't know what is a distill. Deepseek R1 8B IS A DISTILLED Qwen2 .you should be using qwen3 8b-14b instead a lot better
That's literally what I ended up doing in the article tho?
What kind of hardware do we need to run those models?