On: Port of the TypeScript compiler, checker and lsp to Rust, by LLM

[wg0]

Paraphrasing from README.md:

>Spent over $400,000 in API priced tokens with GPT-5.6 Sol and GPT 6 Astra. They wrote over 1.3m lines of Rust over multiple months of /goal loops and never got past like 84% compat.

Then they let Claude code lose on the problem:

> I figured it'd be fun to throw Opus 5.5 at this. It had a working v0 in 10 hours. I assumed it kept using the code the Codex models wrote. I was wrong. Opus 5.5 started from scratch. It got further than Astra in 1/10th the time.

In the warnings from README.md

> Also worth mentioning: I've never read a line of this code.

[orthogonal_cube → wg0]

They spent over $400k for an experimental project and published it without reading a single line of code??

I am so confused about the motivation behind this.

[LelouBil → orthogonal_cube]

They didnt actually spent 400k, that's in "API-priced" tokens, he spent ~$24,047

[orthogonal_cube → LelouBil]

Ok, that makes more sense. If the other comments are correct in saying this was done using a $200/mo personal subscription, I get this is more of a “what is possible, and how much would it cost without subsidized pricing” type of experiment. Thank you for clarifying on that.

[chasd00 → LelouBil]

He didn’t spend that much either. That’s the equivalent API cost using his $200/month subscription. It took less than a day so I guess it cost about $7 in actual money.

[JBits → LelouBil]

How on earth does someone just randomly spend $20k? If he's not going to maintain the project, the whole thing seems completely pointless.

[orthogonal_cube → JBits]

Looks like this is a company’s org which heavily relies on AI. Probably “the cost of doing business” and to see just what can be done with the new model.

[owebmaster → orthogonal_cube]

No, that's not the case. It's a click baity narrative made by an influencer.

[Rapzid → JBits]

Youtuber. It's content.

[epolanski → orthogonal_cube]

> I am so confused about the motivation behind this

Seems obvious, experimenting with what it's possible with LLMs.

[jckahn → orthogonal_cube]

The motivation was to see the result. Why is reading the code an important concern?

[xnorswap → wg0]

I've been rinsing Opus 5.5 and I've been unable to get over 20% of my plan usage, it seems to use a tiny fraction of the usage that Opus4.8 or 5.0 used.

I don't know if it's an accounting trick or genuinely less usage, but since 5.5 I've not had to think about limits at all.

[wg0 → xnorswap]

What plan are we talking about?

[nialv7 → wg0]

throw away $400k on a failed attempt is crazy...

[xedrac → nialv7]

It wasn't $400k in real money.

[globular-toast → xedrac]

What was it then? Who paid the $400k?

[true_religion → globular-toast]

It's theoretical money, because he used multiple subscription accounts that would have cost $400k in token pricing, if he were going via the API.

[globular-toast → true_religion]

What the hell is "theoretical money"? It sounds like either OpenAI took the $400k hit, or their API pricing is utterly bonkers and therefore completely pointless to quote. It would be like me saying my car is worth $400k in theoretical money because, yeah, I'd totally sell it to you for $400k.

[true_religion → globular-toast]

Obviously their API is priced at what the market will bear, not what it actually costs for them to make it available.

It doesn't mean that all price points are fictional, it just means that in edge cases such as this one, the reasoning breaks down.

[dwattttt → globular-toast]

No one. Quoting sibling, it would have been about $7 usage of a $200/month subscription.