Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Assuming you can catch every new bug it introduces.

Both assumptions being unlikely.

You also end up with a code base you let an AI agent trample until it is satisfied; ballooned in complexity and redudant brittle code.



You can have an AI agent refactor and improve code quality.


But, have you any code that has been vetted and verified to see if this approach works? This whole Agentic code quality claim is an assertion, but where is the literal proof?


If it can be trained with reinforcement learning then it will happen


Did we have code quality before llms?


Funnily enough I've literally never seen anyone demo this, despite all the other AI hype. It's the one thing that convinces me they're still behind.


It’s agents all the way down - until you have liability. At some point, it’s going to be someone’s neck on the line, and saying “the agents know” isn’t going to satisfy customers (or in a worst case, courts).


> until you have liability

And are you thinking this going to start happening at some point or what?

The letters I get every other month telling me I now have free credit monitoring because of a personal info breach seems to suggest otherwise.


A firm has very different amounts of time, ability and money to spend on following up on broken contracts.


Sure it can. It's not like humans aren't already deflecting liability or moving it to insurance agencies.


> It's not like humans aren't already deflecting liability

They attempt to, sure, but it rarely works. Now, with AI, maybe it might, but that's sort of a worse outcome for the specific human involved - "If you're just an intermediary between the AI and me, WTF do I need you for?"

> or moving it to insurance agencies.

They aren't "moving" it to insurance companies, they are amortising the cost of the liability at a small extra cost.

That's a big difference.


At some point, the risk/return calculus becomes too expensive for insurance companies.

Usually thats after the premiums become too high for most people to pay.


Just today I had an agent add a fourth "special case" to a codebase, and I went back and DRY'd three of them.

Now I used the agent to do a lot of the grunt work in that refactor, but it was still a design decision initiated by me. The chatbot, left unattended, would not have seen that needed to be done. (And when, during my refactor, it tried to fold in the fourth case I had to stop it.)

(And for a lot of code, that's ok - my static site generator is an unholy mess at this point, and I don't much care. But for paid work...)




Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: