Very good, Code is extremely nice but as others have said, if you let it go on its own it burns through your money pretty fast.
I've made it build a web scraper from scratch, figuring out the "API" of a website using a project from github in another language to get some hints, and while in the end everything was working, I've seen 100k+ tokens being sent too frequently for apparently simple requests, something feels off, it feels like there are quite a few opportunities to reduce token usage.
That was my sense too. Used it for a few similar programs today (like converting HTML to Markdown but parsing certain <figure> elements to shortcodes) and scaffolding a Rust web app.
It's done a reasonable job — but rips through credit, often changing its mind. Even strong-arming it into choosing an approach, it wanted to flip-flop between using regex and lol_html to parse the HTML whenever it came across a difficulty.
If you're a US developer on whatever multiple of $ to the £ that I earn it might make sense, but burning through $100p/h for a pair programmer is a bit rich for my blood.
I've made it build a web scraper from scratch, figuring out the "API" of a website using a project from github in another language to get some hints, and while in the end everything was working, I've seen 100k+ tokens being sent too frequently for apparently simple requests, something feels off, it feels like there are quite a few opportunities to reduce token usage.