Post #2189068

2026-04-02 14:36 UTC

I’m far from convinced that this is actually possible. It’s certainly not now — and I’m not talking about models. Testing and verification tools are nowhere near where they’d need to be, regardless of model quality. Today, code quality DOES still matter; even the best-case version of agentic engineering can’t produce code that’ll never require maintenance. But I can see a possible future where code quality might not matter, or will matter a lot less, and that’s FASCINATING. (3/5)

Replies (5)

@jacob@social.jacobian.org 2026-04-02 21:48

Specifically what I find fascinating is: the tooling that would be required to make agentic engineering begin to live up to the hype — much better testing tools, formal business logic specification languages, more powerful and easier to use formal verification tools, better static analysis tooling, etc — would be massively useful to software engineering quite regardless of the existence/utility/quality of LLMs. (4/5)

Open ##2189069
@troed@swecyb.com 2026-04-02 14:43

@jacob@social.jacobian.org Never thought about the provably correct path. I have seen the "who cares what the code looks like when it's only the AI that sees it" though. But yeah, that's intriguing.

Open ##2189071
@sean@scoat.es 2026-04-02 14:50

@jacob@social.jacobian.org A thought when reading this: even if it were possible to make something perfect (serving your straw man) by today's version of perfect, we know that definition will change over time (e.g. https everywhere today, but not before Firesheep). I think there are some parallels here to “I'm not doing anything wrong, so privacy doesn't matter to me.” The definition of “not doing anything wrong" has changed. Also difficult maintenance via LLM will get *expensive* when it's unsubsidized.

Open ##2189072
@phillmv@hachyderm.io 2026-04-02 15:14

@jacob@social.jacobian.org code quality does not matter *if the code never has to change*. it’s always a forward looking statement: we want easy to understand code because we will have to modify it later. if later never comes then i agree entirely; but in my own very limited explorations imho the LLMs also find good code easier to read and reason about…

Open ##2189074
@gonzalo@social.sdf.org 2026-04-02 21:11

@jacob@social.jacobian.org I mean, we don't care about the machine code quality (not even in performance terms in many cases), so I do think we won't care about code quality in the future, but what I do care is determinism: the same input (prompt) should *always* produce the same output (generated code), I guess it'll come down to a new kind of programming-ish language that somehow provides that?

Open ##2189076