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

read up on llm embedding to start building something new with ollama

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

prototype a simple autocomplete using local llama2 via Ollama #aiplay

🤖 played around with adding extra context in some local Ollama models. Trying to test out some real-world tasks I'm tired of doing. #research

talk about LLM finetuning and Alpaca and ChatGPT being just instruct-text model #life fxtwitter.com/levelsio/status…

🤖 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

🤖 played with Aider and it mostly working with Ollama + Llama 3.1 #research

write blog about LLMs generating dynamic user interfaces so that @adamwathan goes into AI #life x.com/levelsio/status/1735290…

🤖 spent my evening writing a better console for some more advanced Ollama 3.1 projects. #research

dove into pluggy and rebuilt #concord's plugin system

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.

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

research on llm models #life

Ran some local LLM tests 🤖

still prototyping #blinkloader

more research and work on llms and reading up on embeddings

🤖 played with Ollama's tool calling with Llama 3.2 to create a calendar management agent demo #research

more late night llm hackery

Documented use of plugin for site #olisto 📝