Why most AI evals would miss the Linear sales email failure

Y	Hacker News new \| ask \| show \| jobs

	Why most AI evals would miss the Linear sales email failure (tenureai.dev)
	6 points by jflynt76 36 days ago

1 comments

> GroundEval is built around that question...

> This is the same distinction GroundEval makes for question answering agents.

> GroundEval treats agent behavior as something that can be tested against a state contract.

> That is the class of failure GroundEval is designed to catch.

this is an ad shaped like a blog post

For what it's worth, I didn't describe it as anything; just posted the link. It's a paper with open code, no product behind it.