Testing & Bugfixing #morflaxstudio v2

working on lod

Merge website tech + previous found tech #sparkbase

dev -> improved Trial logic #abcgamers

🏎 speeding up clients testsuites with in-memory caches #revsys

scenario, performance and scanner cases passing #bleakio

explored and tested a few tools #tw

🤖 updated #research project to better handle context windows and even an experimental autogpt-like commands

🤖 more sweep work and I optimized the Dockerfile to use a RUN cache

validate performance work #codewithhugo

fix results from Codeformer or GPFGAN different than Clarity because I loaded a LoRa for those #photoai

magic link code generator #neeeds

🤖 worked on a random automation project with copier #mylife

Hooked up Watchdog to the AI model tonight and rule enforcement is working perfectly. Notice I used several tricky example msgs that would be tough for a string matching bot to deal with and still there are zero false positives 🦾🤖 #watchdog

Ran some local LLM tests 🤖

🤖 my CalendarAgent can now read and write to my calendar. I haven't quite figured out how to make it smart enough to know when to look for what's already on my calendar. i was hoping tool calling would work a little better. #research

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

🤖🧹 setup a Wyze robot vacuum to automate cleaning downstairs. So far so good. The software is really good and even maps out the house. #mylife

FINALLY! Made the canvas work. First time using a combo of Llama 3.1, Claude Sonnet 3.5 and ChatGPT, but the trickiest parts were mostly solved by Llama 3.1. Looks like Claude is better for coding with more conventions, not more uncommon stuff like canvas, while I'm pleasantly surprised Llama 3.1 can deliver on it! Now, what should I call this new project... #indiejourney

coding with Claude -- used to save me time, now feels like it's slower than doing everything from scratch #life