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

🤖 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 AI story writing. Also, getting a better handle on what various versions of Llama2 can handle.

tools for new story #starterstory

I used Claude 3.5 Project + Artifacts to help refactor most of the Ollama + Llama 3.1 #research project. I would call it a writing bot, but I'm not building it to automate writing. It's mostly a content wrapper around the Chat interface but it's good at generating code and building off of chat history.

prototype a simple autocomplete using local llama2 via Ollama #aiplay

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

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

basic tools form for stories #starterstory

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

✏️ wrote about running Llama 3.1 locally through Ollama on my Mac Studio. micro.webology.dev/2024/07/24…

📝 prototyped an llm-ollama plugin tonight. models list and it talks to the right places. prompts need more work.

Playing with llama2 locally and running it from the first time on my machine

some lunch time llm work and ported hubcap.php to Python which was easy peasy

working on naming ideas before I OSS one of my Python/Django code gen tools

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

prototyped a light-weight python based pipeline tool because I'm tired of people rolling a huge stack for this

check out Llama 3.1 #life

researched how to write an Alfred plugin using Python. Not too bad. #mylife

write tools plan #pasfoto