#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

#thecompaniesapi port back my ai wrapper improvements on our existing llama stack and prepare fine tuning for phi3

#thecompaniesapi port back my ai wrapper improvements on our existing llama stack and prepare fine tuning for phi3

updated story writer to use chatgpt and llama2 to smooth out some issues where large context windows would be helpful

🤖 lots of AI research last night including writing a functional story bot to wrap my head around how to apply step-by-step logic and get something meaningful out of llama2 #research

🤖 more working with Ollama and Llama 3.1 and working on a story writer as a good enough demo. #research

#thecompaniesapi lots of fixes on the queue ; trying to get the llm stable ; refactor of sources

work on #crisp ai features improvements

#thecompaniesapi continue working on phi3 ; first steps of subdomain support & association ; rewrite most of our AI impl

check out Llama 3.1 #life

checking AI work #bagsoup

worked on llama2 experiments mostly to see how easy it is to break it and how good the overall quality is.

Start working on new AI project

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

got distracted with my writer AIs — testing between llama3.1 vs gemma2 #leifinlavida

switch #therapistai to Llama 3.1

hacking on new AI side project

try client side web based Llama 3 in JS #life webllm.mlc.ai/

study Stanford’s Alpaca instruction model finetuning for LLaMA source data #life

Work on #3dicons AI