segalord

based it off this 2017 dataset from UCSD (https://cseweb.ucsd.edu/~jmcauley/datasets/goodreads.html)

some fun writing CUDA accelerated code to cluster the data and then find similarity scores

LiteLLM has like a 1000 dependencies this is expected https://github.com/BerriAI/litellm/blob/main/requirements.tx...

I love your poetry on a phone project so muchhhh

this is every data hoarders dream setup haha

> The thing that I appreciate most is that the company is that it "walks the walk" in terms of distributing the benefits of AI. Cutting edge models aren't reserved for some enterprise-grade tier with an annual agreement.

That is literally how openAI gets data for fine-tuning it's models, by testing it on real users and letting them supply data and use cases. (tool calling, computer use, thinking, all of these were championed by people outside and they had the data)

Man googles offerings are so inconsistent, batch processing has been available on vertex for a while now, I dont really get why they have two different offering in vertex and gemini, both are equally inaccessible

Xd, Gotta love how your first question to a test a model is about a “ruliad”. It’s not even in my ios dictionary

You’d still be reasoning using symbols, language is inherently an extension of symbols and memes. Think of a person representing a complex concept in their mind with a symbol and using it for further reasoning

I use it exclusively for users on my personal website to chat with my data. I've given the setup tools to have read access my files and data

Noticing CF pushing for devs to use DO for eveything over workers these days. Even websocket connections on workers get timed out after ~30s and the recommended way is to use DO for them

My man’s got a legal notice out against him

How are you planning to train a model based on annotated actions done on a page? Wouldn’t it be more practical to have a model like PIX2ACT that understands the action to be performed and does it? Or are you planning to compose future actions from decomposing flows?

Just give us accesible hardware kill switches on the side and I'm sold

I remember my mom reading these for me, and I'd go "what kind of a name is Ilya?" And years later at University our elective humanities professor explained in detail how Soviet and American propaganda worked in the older days and that was when I truly understood

Thank you for this, I'll proceed to add them to my RSS feed