Co-designing a sparse music codec with ChatGPT o3 • Hacker News Board

Re: Co-designing a sparse music codec with ChatGPT o3

#21

Post by avaku » Wed, Apr 30, 2025, 10:15 AM UTC

th0ma5 wrote: post #9

_bin_ wrote: post #7

Earlier quoted context omitted.

I don't know if it's a skill issue but there seems to be a ceiling to the problem complexity it can handle. It's alright for web but I haven't gotten great results from anything more. It also falls over when you need it done your way, not the model's preferred way (aka whatever is most likely). When you need a UI library besides shadcn. When you're using Svelte over React. Etc. It would be really constructive if peop…

I can't upvote ya enough. There's some kind of Clever Hans thing where people aren't honest with how much fudging they have to do, or how brittle the results are.

I made this blog post, because I did very little fudging and was shocked by how good the results are. However, this only happened with the latest model (o3). That's why I wanted to describe my approach. First, give AI the model / architecture description, and make sure it understands. Then proceed to the code.

Re: Co-designing a sparse music codec with ChatGPT o3

#22

Post by avaku » Wed, Apr 30, 2025, 10:16 AM UTC

jstanley wrote: post #15

th0ma5 wrote: post #10

Earlier quoted context omitted.

Do AI commentators only expect to be read by AI fans?

I am an AI fan, I just thought the random specific irrelevant details sprinkled in the middle were out of place in such a high level overview. One technique I use is to paste a draft into a new conversation and let ChatGPT work on it some more without the context from your earlier chat. You can do this several times.

You're right, your comment is valid. I will make better blog posts in the future :)

Re: Co-designing a sparse music codec with ChatGPT o3

#23

Post by _bin_ » Wed, Apr 30, 2025, 7:53 PM UTC

avaku wrote: post #21

th0ma5 wrote: post #9

Earlier quoted context omitted.

I can't upvote ya enough. There's some kind of Clever Hans thing where people aren't honest with how much fudging they have to do, or how brittle the results are.

I made this blog post, because I did very little fudging and was shocked by how good the results are. However, this only happened with the latest model (o3). That's why I wanted to describe my approach. First, give AI the model / architecture description, and make sure it understands. Then proceed to the code.

Yep, I've heard many people have much stronger results with o3 and am glad it's working for them! I think it would help if you could dig up and publish at least a few of your chats through ideation/architecture, initial implementation, refinement, testing, etc. It might help those of us luddites who can't seem to make even o3 work the way we want it to.