Hacker News new | ask | show | jobs
by jampekka 50 days ago
There are of course limits to what prompting can do, but it does steer the models.

In TFA they found that prompting mitigates over-editing up to about 10 percentage points.

1 comments

Similar to the observation (by simonw) that they respond reasonably to "TDD: Red => Green"

I've used that ever since. Works most of the time, but other stuff is often failing and I've learned to become distrustful of an agent very quickly. One mistake where I point it out and the agent corrects itself is fine if it keeps working well after. A second mistake when it's trying to fix the first one or an inability to understand or a claim that it fixed it but it didn't is instant termination (after dumping context for the next agent).