News for hackers. Stuff that matters.

paletov

Re:Show HN: CAD with AI on Monday September 16, 2024 @11:46AM (#41557263)
Please note that this is currently optimized for parametric modeling of functional components, not organic shapes.
Re:Show HN: CAD with AI on Monday September 16, 2024 @11:43AM (#41557229)
Thanks! It’s a mix of some off-the-shelf models with custom training for CAD tasks.
Re:Show HN: CAD with AI on Monday September 16, 2024 @11:43AM (#41557222)
Thanks for the interest! Yeah, it does use OpenSCAD under the hood. The parameter names are something I'm still tweaking—glad to hear they worked well in the headphone hanger example!
Re:Show HN: Shelly: Write Terminal Commands in English on Wednesday January 17, 2024 @02:35AM (#39024500)
Currently it returns:

grep -r --exclude-dir=.venv "class" .

Re:Show HN: Shelly: Write Terminal Commands in English on Wednesday January 17, 2024 @02:21AM (#39024387)
My understanding is that ShellGPT aims to be a complete OS assistant. It's similar to Open Interpreter (https://github.com/KillianLucas/open-interpreter).

Shelly is a mini tool at the moment that only generates and executes commands for you.

Re:Show HN: Shelly: Write Terminal Commands in English on Wednesday January 17, 2024 @02:07AM (#39024264)
It opens the command in nano/vim in the terminal and lets you edit it. Saving executes the final version.

Currently, the user has to be experienced enough to know if a command is safe to be executed. However, you are right, and I'll look into adding a safety feature that signifies if a command is potentially dangerous.

Re:Show HN: Shelly: Write Terminal Commands in English on Wednesday January 17, 2024 @02:01AM (#39024224)
It's too early for cowboy mode. The LLM isn't reliable enough to let it run commands without approving them first.

As others noted, "try" could be used to make the commands testable, so I'll look into it this weekend.

Re:Show HN: Shelly: Write Terminal Commands in English on Sunday January 14, 2024 @02:07AM (#38988198)
Yeah, that would be bad. That's why I added an intermediate step.

It opens the command in an editor like when you run "git commit", so you can edit it. Saving executes the final version.