
Follow ZDNET: Add us as a preferred source on Google.
ZDNET’s key takeaways
- Codex struggled with big-picture debugging across complex codebases
- Deep Research excelled at diagnosis when code context spanned versions
- Human testing and oversight still remain critical with AI coding
“Huh?!?” Sometimes, when I’m coding and something doesn’t behave quite right, and I’m not entirely sure what’s up, my brain fires off an internal “Huh?!?” I think it’s my way of recognizing…








