ollama is worth using if you have an M1/M2 mac and want a speedy way to access the various llama2 models.

livecode even more WebRTC stuff

try Jan.AI LLM app MacOS local client side #life

quick livecode; get useAuth almost working as a lib

livecode some basic gatsby setup #serverlesshandbook

livecode some research #learnwhileyoupoop

livecode some progress #threadcompiler

get a NoCode client #labs

install finally ollama with llama3 #life

#thecompaniesapi run my phi3-128k flow using llama3.1 and the results are mind blowing, it's insane how good llama is at conserving context and original purpose even when supplied with thousands of tokens; also shipped multiple hotfixes in robot UI; about to merge a month of work and then hop on fine tuning

livecode progress on my little CMS #codewithswiz

more fun with LLAMA2 and figuring out how to better control/predict stable output

livecode messing around with Remix

livecode messing around with nextjs #codewithswiz