Re:GitHub Copilot Coding Agent
by OutOfHere on Monday May 19, 2025 @12:59PM
(#44031898)
In my experience in VSCode, Claude 3.7 produced more unsolicited slop, whereas GPT-4.1 didn't. Claude aggressively paid attention to type compatibility. Each model would have its strengths.
[ Parent
| on HN ]
There are no comments on this comment yet.