Coding assistants are solving the wrong problem

Re:Coding assistants are solving the wrong problem by KptMarchewa on Tuesday February 03, 2026 @05:20AM (#46869104)

Why would you ever, outside flight and medical software, care about being 100% sure that the change did not introduce any bugs?

[ Parent | on HN ]

Re:Coding assistants are solving the wrong problem by jacquesm on Tuesday February 03, 2026 @05:25AM (#46869140)

Because bugs are bad. Fixing one bug but accidentally introducing three more is such a pattern it should have a name.

[ Parent | on HN ]

Re:Coding assistants are solving the wrong problem by KptMarchewa on Tuesday February 03, 2026 @05:50AM (#46869296)

They are. And we have processes to minimize them - tests, code review, staging/preprod envs - but they are nowhere close to being 100% sure that code is bug free - that's just way too high bar for both AI and purely human workflows outside of few pretty niche fields.

[ Parent | on HN ]

Re:Coding assistants are solving the wrong problem by jacquesm on Tuesday February 03, 2026 @06:03AM (#46869390)

When you use AI to 'fix' something you don't actually understand the chances of this happening go up tremendously.

[ Parent | on HN ]

Re:Coding assistants are solving the wrong problem by miningape on Tuesday February 03, 2026 @06:13AM (#46869471)

I propose "the whack-a-hydra" pattern

[ Parent | on HN ]

Re:Coding assistants are solving the wrong problem by jacquesm on Tuesday February 03, 2026 @06:19AM (#46869513)

Hehe, yes, very apt. It immediately gives the right mental image.

[ Parent | on HN ]

Re:Coding assistants are solving the wrong problem by bandrami on Tuesday February 03, 2026 @05:29AM (#46869162)

Because why would you make something broken when you could make something not broken?

[ Parent | on HN ]

Re:Coding assistants are solving the wrong problem by KptMarchewa on Tuesday February 03, 2026 @05:50AM (#46869299)

Because it's way too high bar to be 100% sure outside of few niche fields.

[ Parent | on HN ]