Viewing profile — michaelgiba

> You surely aren't implying that the model is sentient or has any "desire" to give an answer, right? The model is a probabilistic machine that was trained to generate completions …

It’s not surprising that there could be a very slight quality drop off for making the model return its answer in a constrained way. You’re essentially forcing the model to express …

73% of startups are just writing computer programs

Interesting idea. Although I wouldn't consider `but restrict the data set to publications from If you did have access to a high-quality pretraining dataset and you could explore tr…

Crazier ideas would be: - extend the concept to also have some sort of “agent mode” where the llamafiles can launch with their own minimal file system or isolated context - detaile…

I’m glad to see llamafile being resurrected. A few things I hope for: 1. Curate a continuously extended inventory of prebuilt llamafiles for models as they are released 2. Create b…

They stopped publishing images, not like they changed anything significant about the product itself. Frankly the whole thing is not newsworthy

For anyone curious here is an interactive write up about this http://michaelgiba.com/grammar-based/index.html

This is much more thorough, but here is an interactive post covering the related topic constrained sampling I put together a few weeks back: http://michaelgiba.com/grammar-based/in…

I was inspired by https://news.ycombinator.com/item?id=43586380 to simulate the reality TV show "The Traitors" using open-source LLMs. I used all open source via either groq or loc…

I was inspired by your project to start making similar multi-agent reality simulations. I’m starting with the reality game “The Traitors” because it has interesting dynamics. https…

Hello HN, I wanted to share a project I have been working on recently called "plomp". It is intended to be a drop-in way to gain visibility into python programs which are prompting…

Nice, I’m particularly excited for the tiny models.

I like the idea but I would hesitate to upload my API keys. why not make the prompting/orchestration pieces open source? A user could run locally to generate a result and the app c…

A different, darker way to interpret this is computers cannot be held accountable today If systems (presumably AI-based) were conscious or self-aware they would very much be incent…

Gemini has had this for a month or two, also named "Deep Research" https://blog.google/products/gemini/google-gemini-deep-resea... Meta question: what's with all of the naming over…

Hi all, I wanted to share a side project I’ve been working on for a while which, given a link to a news article, produces an animated late night show of configurable length and sty…

This is art

it’s pretty impressive that PyTorch is only 7% slower than this given it can be used so generally

I am not sure either. Although maybe it just comes down to how the purchased compute is “delivered”