A look at Cloudflare's AI-coded OAuth library

Re:A look at Cloudflare's AI-coded OAuth library by bradly on Sunday June 08, 2025 @08:11AM (#44216488)

I've found llms are very quick to add defaults, fallbacks, rescues–which all makes it very easy for code to look like it is working when it is not or will not. I call this out three different places in my CLAUDE.md trying to adjust for this, and still occasionally get.

[ Parent | on HN ]

Re:A look at Cloudflare's AI-coded OAuth library by pennomi on Monday June 09, 2025 @10:07AM (#44224689)

Agreed, I’ve found that LLMs favor wrapping entire functions in broad try:catch structures, making it nearly impossible to identify and debug problems. Dangerous if you don’t correct it.

[ Parent | on HN ]