I can be massively more ambitious when coding with AI, but most importantly I have zero emotional investment in the code so I can throw it away and start again whenever I want.

> Posting it on a Show HN or Product Hunt

and funnily enough, this is still marketing

"build it and they will come" doesn't work

I don't know a lot about 3D modeling, but I can see that the objects created by this AI are way too high poly, which would be bad for performance if used e.g. in a game. But it still looks like a great prototyping tool to me, especially if you want to express an idea in your head to an actual 3D designer, in the same way UX designers can show a prototype to developers with Claude code now, instead of trying to repro an idea with Figma.

I don't agree with the author. Where is the part about nondeterminism and hallucinations? Drawing a pretty chart doesn't make the argument true. All these benchmarks and competitions are on problems that have a _right answer_. I write most my code entirely through Claude at work and have Claude Max for personal, and I can see every day that even with the right context, it's not certain that the model is going to converge to a decent answer on complex real life issues. At least one thing I do agree on: model growth is not an exponential, like everyone thought when we were on the first leg of it, but a logarithmic.

The Netscape theme is my favorite. Love the pixel-y cursor animation

Man I used python sparingly over the years and I still had to deal with all those package manager changes. Worse than the JS bundling almost?

No, the JS bundling changes are almost monthly and it's impossible to know which one should I use and what will be broken because of my choice.

Other than a brief stint with yarn (v1) I've never had any of these troubles with node+npm

This looks very charming, but how do you keep it dusted/clean practically?

Small room size helped a lot: Blueair HEPA filter with a (long, think Ostrich) feather duster for day to day, and ~ weekly wet wipe / vacuum.

I hope that they are going to put something in Claude Code to display if you're entering the expensive window. Sometime I just keep the conversation going. I wouldn't want that to burn my Max credits 2x faster.

Yeah, that 1 MM tokens is a $15 (IIRC) API call. That's gonna add up quick! My favorite hypothetical AI failure scenario is that LLM agents eventually achieve human level general intelligence, but have to burn so many tokens to do it that they actually become more expensive than a human.

I believe Claude Code uses cache aggressively, so this 1kk tokens will be 90% discounted or do I miss something?

Have it generate the code. Then have another instance criticize the code and say how it could be improved and why. Then ask questions to this instance about things you don't know or understand. Ask for links. Read the links. Take notes. Internalize.

One day I was fighting Claude on some core Ruby method and it was not agreeing with me about it, so I went to check the actual docs. It was right. I have been using Ruby since 2009.

> Aider is much nicer, from the standpoint that you can add the files you need it to know about, and send it off to do its thing.

Use /add-dir in Claude