Back
Similar todos
overhauled another scraper/processor with much better tests and fixed several non-obvious bugs. I should have written tested upfront.
🤖 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 my evening writing a better console for some more advanced Ollama 3.1 projects. #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.
🤖 dove a little deeper into a screenshots to code tool and the results are getting much better #research
🤖 Tried out Llama 3.3 and the latest Ollama client for what feels like flawless local tool calling. #research
created several personal AI agents via ollama 
#leifinlavida
check my NeRFs from OpenAI Sora videos and see 2 actually generated succesfully 
#life lumalabs.ai/capture/57fe12f4-… lumalabs.ai/capture/bc2e0757-…
🐳 switched my ci/deploy process completely over to GitHub Actions and GitHub Package Registry 
#conf
🐍 🤖 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.
🤖 ported a few bots to docker 🐳 and consolidated repos 
#bots
got distracted with my writer AIs — testing between llama3.1 vs gemma2 #leifinlavida
✏️ I wrote and published my notes on using the Ollama service micro.webology.dev/2024/06/11…
🐙 yesterday on GitHub 
#oss
🐙 yesterday on GitHub #oss
🐙 yesterday on GitHub #oss
🐙 yesterday on GitHub #oss
