A good way to get a model to answer questions about a codebase without overwhelming it or exceeding its token count is to: 1. just give it the directory structure 2. ask it questions based on that 3. after it answers a question ask it if there are any specific code files it needs to better answer the question you asked 4. attach only those files so it can confirm its answer and back it up with code

you can upload a zip of a feature files as they are in the project and ask to implement it on another platform on chatgpt 4.5, works pretty good.

Perhaps this could include scores from multiple sources, similar to how google displays them when you search for a movie.

Yes, I am planning to introduce atleast rottentomatoes ratings at first. Wanted to validate idea first.

Would love the RT connection, especially if it has both critics and user scores. IMDB usually tells me nothing but "This sucks, don't watch it" (score of 5.X) but I don't get anything else from their ratings.

Hey, I'm the guy who made this! Happy to answer any questions that the blog didn't address

Do you think you could get this to work for Google Assistant as well?

Does ASL-to-text already exist outside of voice assistants, or is that part totally new?

yup you definitely have to keep that in mind while designing. luckily the projet 7000 SLA printer, prints with supports that are actually a pleasure to remove.. You have to be more careful about preventing resin accumulation in any part as it could cause deformations

:D

thank you :)

thanks, glad you liked it.. I have a love-hate with these kinds of projects

I missed Step 3!

There is no step 3.

???

:D thanks

polaroid actually recommended against shaking so I decided to do away with that.. was thinking of adding an accelerometer before that to trigger the reveal