Looking forward to seeing the stats.

I gave it an abandoned repo for an Aseprite MCP someone made and told it to iterate with a laundry list of things I wanted from it to include thousands of plugins.

Came back 20 hours later and it shit out a pretty surprising little tool, will post the public repo when I get time.

As long as you have enough money to throw billion dollar darts at a trillion dollar dart board you're gonna skate out cleanly every time. There's a bigger problem here and everyone knows it.

so weird this is at the top. I just wrote an article yesterday about zuck and the masterclass that the meta ray-ban glasses are.

Wearables ain't going anywhere but up.

What was the dataset this was trained on? I ask because it's pretty good.

No dataset. I'm using two types of prompts to direct the LLM on outputs, an overall system prompt that applies to all the outputs and eight style prompts corresponding to each of the eight cringe categories.