A whole codebase of 100k lines (~1M tokens) for ~a dollar. Would like to understand why would signing up for this be shocking?

▲

rowanG077 5 days ago | parent [-]

That's really misrepresenting how it works. Most lines will be written, re-written again and adjusted multiple times. Yesterday I did approx 5 hours of peer-coding with claude 4 opus. And I have these stats:

Total tokens in: 3,644,200 Total tokens out: 92,349

And of that only approx 2.3k lines where actually commited for PRs.

▲

simonw 5 days ago | parent | next [-]

I calculate that as $61.59 https://www.llm-prices.com/#it=3644200&ot=92349&ic=15&oc=75

So that's about $12/hour, or 2.6 cents per line of finished code.

Still pretty cheap! Very few unassisted human programmers can churn out 2300/(5 * 60) = 7.6 lines of code per minute consistently over a five hour time span.

That said, I think Claude Code, while impressive, is incredibly quick to burn through tokens. I still mostly use copy-and-paste info Claude or ChatGPT as my main AI-assisted workflow which keeps me in more control and spends a ton less tokens.

▲

rowanG077 5 days ago | parent [-]

Yes I can confirm that's approx what I paid. My first time using claude 4 opus and I used aider. It seems the estimation aider gives is very wrong as it was telling me I used approx 15$. I only noticed because my credit ran out. The $/performance tells me I should check what grok4 can do. I didn't use it seriously yet.

	▲	simonw 5 days ago \| parent [-]
		Claude Opus 4 is 5x the price of Claude Sonnet 4. I don't think it's 5x as good. I default to Sonnet and rarely use Opus - in this case Sonnet would have cost about $12.31 for the same volume of tokens.

▲

0points 5 days ago | parent | prev [-]

There are code generators for CRUD. You could be a 10x AI programmer without AI if the measure is how fast you bang out CRUDs.