🤖 more agent work and organizing them into a team #research

switch #therapistai to Llama 3.1

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

🧑‍🔬 researching when Llama 2 is as good or better than GPT-4 and when it's not as good. Good read here www.anyscale.com/blog/llama-2…

⬆️ upgraded ollama and tried out some new features

✏️ I wrote and published my notes on using the Ollama service micro.webology.dev/2024/06/11…

🔨 I have prompts working (but not streaming) with llm-ollama. It needs a lot of work and polish still.

#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 working on llama3.1 with large context window, trying to improve some parts of our AI flow before merging it; now properly respects industries & naics constraints for current sample

prototype a simple autocomplete using local llama2 via Ollama #aiplay

tools for new story #starterstory

Work on new #booklet writing UI

🤖 Took a stab at rewriting parts of Claude Engineer to make file and project storage better. #research