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

🤖 more AI writing project

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

more AI research tonight and sketching out a few practical examples to document/write about

🤖 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

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

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

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

🤖 got llama-cpp running locally 🐍

worked on a few AI projects tonight #research

🤖 learning how to write a GitHub bot youtu.be/Bs_mqDHvCUs #mylife

🐍 🤖 used the Python llm and symbex libraries to write a bunch of code for me while my kids were taking a nap. Not bad. Not bad at all.

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.

install llama2 and come up with a rough draft of a story writing tool with Python. This is deceptively easier than it should be.

Experiment with AI 🧪🧠

🤖 sat down and had ChatGPT write some GPT4(ish) code for me

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

🤖 created a slackbot demo to try out a few ideas with #bots

Tweet about how I made my AI TouristItinerary bot to fetch from my local LLM instead of from OpenAI x.com/rrmdp/status/1727341691… #life

🤖 Wrote a git commit message bot using an LLM to create better commit messages #research