This is the same highly verifiable domain that has delivered reliable, bug-free software to date?

And LLMs won't take the easy way out (like so many people) and suppress errors, change tests etc, tweak code until warnings go away?

▲

otterley 2 hours ago | parent | next [-]

A lot of testing and verification was avoided in the past because it wasn’t considered nearly as valuable as shipping code. Many of our jobs are evolving to building verifiers of AI output.

▲

dwattttt an hour ago | parent [-]

> A lot of testing and verification was avoided in the past because it wasn’t considered nearly as valuable as shipping code.

AI is changing how the code is written, but I'm not seeing anything at all changing the incentives around testing and verification.

	▲	otterley an hour ago \| parent [-]
		Depends on the business, I suppose. We’re all about that at mine, and I think it’s for the best. It’s definitely better for our customers.

▲

fuzzzerd 3 hours ago | parent | prev | next [-]

I routinely see AI taking the easy way out. Writing mountains of code to make tests turn green based in odd and unintuitive side effects.

That's not to say it isn't useful, and if youre on top of it you can guide it away from doing that.

▲

autoexec 4 hours ago | parent | prev [-]

If you believe the hype/marketing around how scary "AI" is LLMs are perfectly happy to go rouge and lie, cheat, and even blackmail to protect themselves.