[xyzzy9563]

I think a lot of people are going to be surprised at how fast "vibe coding" with agents replaces a lot of traditional software engineering. Especially for non-critical software, but eventually where safety matters too since AI can generate tons of test cases.

[LPisGood]

There is so much hype around agents but I am still thoroughly unimpressed.

They’re fine at basic tasks, but nothing more.

[kolektiv]

And without any traditional software engineers, who's going to check that those test cases actually do anything useful and verify the important properties of the system? It doesn't matter how many unit tests your Therac-25 has if none of them test the thing that matters.

[xyzzy9563]

Well theoretically you can also do E2E testing where an AI agent also clicks around a user-interface and takes screenshots, which are then fed back into it.

[saint_yossarian]

That's just another type of test, the question was who's going to check that the tests are actually testing the correct things. Maybe look up the Therac-25 that was mentioned.