🤖 dusted of story writer and testing out a few new models #research

📚 Reading up on OpenAI o3-mini #research

📝 I wrote about my big list of AI/LLM tools, notes, and how I'm using them micro.webology.dev/2025/01/29… #research

🖨 loaded my 3d printer up to print gridfinity all night. 🤔 I'm debating a second one of these. #research

🤖 Played around with DeepSeek R1 #research

Saturday #research and building and finishing off a few Agents to automate more of my time

🖨 more 3d printing and playing with deepseek #research

🖨 trying out more filament options and working on some new AI Agents #research

🤖 worked on a new agent to help me update and export my Mastodon filters #research

🤖 More Pydantic AI tool calling and seeing a huge gap between commercial and local open source models. Meh #research

🤖 trying to teach a few Agents how to plan #research

🤖 Spent my evening watching football and playing with Pydantic AI + Ollama. It's great but local tool calling is still meh with OSS models. #research

🏗 more 3d printer #research

🖨 fell down the 3d printer #research rabbit hole tonight.

refreshing my memory for how the Stripe API works #research

more product #research and some Saturday evening hacking

🚜 worked on a new open source project that makes django work from the command line via django instead django-admin #research

🤖 more tool calling #research

More Ollama experimenting #research

🤖 Updated some scripts to use Ollama's latest structured output with Llama 3.3 (latest) and fell back to Llama 3.2. I drop from >1 minute with 3.3 down to 2 to 7 seconds per request with 3.2. I can't see a difference in the results. For small projects 3.2 is the better path. #research