Whenever you guys have a chance, you have to checkout the new OpenAI model! It's INSANE!!! Here's a link if you want to read more about it: https://openai.com/o1/ So far, I've used this model to help me with a bug that I've been really stuck on at work and it solved it instantly! I've been bouncing back and forth between Claude and ChatGPT-4o for support but neither could help me solve the issue. Right when, o1 came out, I tried it and it solved the issue instantly! Please let me know what you think of the model when you get to try it out on your projects!

II have seen quite a few people asking about GPU sizing for running LLM's recently. I just found the following article on Medium, which lays out a formula for calculating such things. However, this article failed to cite the origin, which is here. Also, in the original article, I found a link to an excellent program: "Can you run it? LLM Version," hosted on Hugging Face. The article and the tool are worth a look, even if it is just for curiosity's sake. And just because it's the weekend, here is some Transformer Math 101 in case you haven't seen it. I hadn't. There may be a test later :P

Trying to get some inspiration and ideas for my next crew..

Project that one of my colleagues in New Society is working on, Jan. Really strong project and here he is using example of how to add Agent Zero as a tool to your CrewAI project. This is a simple example! https://youtu.be/_Pionjv4hGc?si=BfaXAnRDrAyl9O7z&t=2160

Has anyone here done any fiddling with Mojo? https://en.m.wikipedia.org/wiki/Mojo_(programming_language))) https://mojolang.org https://www.modular.com/max/mojo