Especially giving the lack of trust organizations rightfully have in big AI companies
My current workflow is passing a human written spec to an agent to implement with strict coding guidelines, architectural decisions, etc. The agent isn't making any decisions about the abstractions to use, it's just creating the objects and test suites. So I don't mind the slower bandwidth because I'm running the heavy agentic lifting over night with no need for human supervision.
But I fully appreciate that my workflow isn't the norm. In fact my workflow it's the exact opposite the AI grifters like Sam Altman are selling because it still involves a human with knowledge of the systems making different decisions.
I just wish I could buy enough memory to run one of these models locally. Specially Kimi K3
This guys an Alpha Fail
I guess Sam Altman is getting his legal advice from ChatGPT
I'm assuming the pork ribs had sources
This isn't true. He says enough stupid things without having to make things up. https://www.yahoo.com/news/politics/articles/fact-check-robert-f-kennedy-233148881.html
Build it with Fable 🤷♂️
We probably need to build a pipeline over the border
We also have a land border with Denmark
He's more akin to Stalin. Trump has an incompetent indifference to the US population. If he had acted earlier during COVID he could have prevented at least 100K unnecessary deaths. And then he goes and gets the vaccine in secret. Sure he hasn't killed as many people as Stalin yet but given his policies on climate change it's very possible his actions will lead directly to more deaths than Stalin and Hitler combined. Only time will tell and our descendants will not judge people like trump kindly.
I've got 128GB RAM + 24GB VRAM on a 4090. I've managed to get a 400B parameter model running on a single board computer with 64GB RAM by using MMAP. But I want to run Kimi K3 locally so I would need a lot more RAM / bandwidth