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

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

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

🤖 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

🤖 spent some time getting Ollama and langchain to work together. I hooked up tooling/function calling and noticed that I was only getting a match on the first function call. Kind of neat but kid of a pain.

🤖 got llama-cpp running locally 🐍

🤖 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

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

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.

🤖 still sick but played with playwright and developed a pretty cool bot framework. might use that to automate more common tasks #mylife

check out Llama 3.1 #life

Shipped BoltAI v1.13.6, use AI Command with local LLMs via Ollama 🥳 #boltai

🤖 worked on my #research project and use Claude's project + artifacts to help reactor and add a bunch of new features to it.

⬆️ upgraded ollama and tried out some new features

🤖 tried to setup tailscale serve to access Ollama and it's not happy

🤖 worked on old scraping project and making playwright act like a real person

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

prototype a simple autocomplete using local llama2 via Ollama #aiplay

switch #therapistai to Llama 3.1

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