mogili

Ya it's not very usable compared to Claude / codex

It can be single motor too.

These are essentially zero-shot classifiers; they don't need to be trained for a specific classification task. You could include some natural language context on the rules for classification and it should get good enough accuracy.

I've found Gemini to be better at writing. Claude has gotten worse while it gets better at coding / agentic use cases.

Wasn't just a review, it failed the task I gave and Opus completed the task

It's not a good model tbh, got a bunch of things wrong that Opus corrected in my codebase.

It uses the word load bearing a bit so I'm guessing either Anthropic or Claude distilled model.

3d printing is great for low volume parts that have challenging geometries. The aerospace industry has been talking about 3d printed parts for a long time now.

They do have an ambient mode you can enable.

It means it'll use tool calls to search slack and get context not that it's some sort of ambient always running loop.

Token consumption on this is not a huge issue, I built this a few months ago for our company slack using claude agent sdk and most of the conversations/sessions were short lived. You don't generally tend to have long sessions with agents in Slack like you would if using in the terminal.

It was very useful to delegate things like create a ticket based on a discussion to Claude.

This is a solved problem, there are many that do this. Can't believe YC would fund this in 2026.