Or not. I watched Copilot's agent mode get stuck in a loop for most of an hour (to be fair, I was letting it continue to see how it handles this failure case) trying to make a test pass.
Yeah! When that happens I usually stop it and tap in a bigger model to “think” and get out of the loop (or fix it myself)
I’m impressed with this latest generation of models: they reward hack a lot less. Previously they’d change a failing unit test, but now they just look for reasonable but easy ways out in the code.
I call it reward hacking, and laziness is not the right word, but “knowing what needs to be done and not doing it” is the general issue here. I see it in junior engineers occasionally, too.
Or not. I watched Copilot's agent mode get stuck in a loop for most of an hour (to be fair, I was letting it continue to see how it handles this failure case) trying to make a test pass.