Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

When AI writes the software, who verifies it?

leodemoura.github.io

Post reply on HN
Print view View original

211–220 of 309 posts

Re: When AI writes the software, who verifies it?

#211

Post by globular-toast »

neya wrote: post #161

The fundamental problem is the verification loop for the average developer is grounded not in tests, but with results . Write code, reload browser, check output. Does it work the way I want? Good. We're done here. Not write code, write tests, ensure all test-cases are covered. Now, imagine such a flaky foundation is used to build on top of even more untested code. That's how bad quality software (that's usually unfix…

This is actually how a lot of software is written, sadly. I used to call it "trial and error programming". I've observed people writing C++ who do not have a mental model of memory but just try stuff until it compiles. For some classes of software, like games, that is acceptable, but for others it would be horrifying.

Now, it is actually completely possible to write UI code without any unit tests in a completely safe way. You use the functional core, imperative shell approach. When all your domain logic is in a fully tested, functional core, you can just go ahead and write "what works" in a thin UI shell. Good luck getting an LLM to rigidly conform to such an architecture, though.

Re: When AI writes the software, who verifies it?

#212

Post by scotty79 »

roadbuster wrote: post #139

> The Claude C Compiler illustrates the other side: it optimizes for > passing tests, not for correctness. It hard-codes values to satisfy > the test suite. It will not generalize. This is one of the pain points I am suffering at work: workers ask coding agents to generate some code, and then to generate test coverage for the code. The LLM happily churns out unit tests which are simply reinforcing the existing behavi…

> The LLM happily churns out unit tests which are simply reinforcing the existing behaviour of the code.

I always felt like that's the main issue with unit testing. That's why I used it very rarely.

Maybe keeping tests in the separate module and not letting th Agent see the source during writing tests and not letting agent see the tests while writing implemntation would help? They could just share the API and the spec.

And in case of tests failing another agent with full context could decide if the fix should be delegated to coding agent or to testing agent.

Re: When AI writes the software, who verifies it?

#214

Post by himlion »

scotty79 wrote: post #213
tbossanova wrote: post #173

Earlier quoted context omitted.

Once upon a time people advocated writing tests first…

I wasn't able to force the agent to write failing tests yet. Although I'm sure it should be possible to do.

I do that all the time with Claude. What part is not working?

Re: When AI writes the software, who verifies it?

#215

Post by alexsmirnov »

SoftTalker wrote: post #172
roadbuster wrote: post #139

> The Claude C Compiler illustrates the other side: it optimizes for > passing tests, not for correctness. It hard-codes values to satisfy > the test suite. It will not generalize. This is one of the pain points I am suffering at work: workers ask coding agents to generate some code, and then to generate test coverage for the code. The LLM happily churns out unit tests which are simply reinforcing the existing behavi…

Um, you're supposed to write the tests first. The agents can't do this?

Actually, they extremely bad at that. All training data contains cod + tests, even if tests where created first. So far, all models that I tried failed to implement tests for interfaces, without access to actual code.

Re: When AI writes the software, who verifies it?

#216

Post by phyzix5761 »

I found my best use of AI for writing code is with a TDD approach. I write 1 test, watch it fail, let the AI implement the solution, and then if I like it I commit. Write the next test and repeat.

It keeps me in the loop, I'm testing actual functionality rather than code, and my code is always in a state where I can open a PR and merge it back to main.

Re: When AI writes the software, who verifies it?

#217

Post by waterTanuki »

I've grown to hate using python in production since LLMs have been around. Python cannot enforce minimum standards like cleaning up unused variables, checking array access, and properly typing your functions. There's a number of tools built to do this but none of them can possibly replace a compiler.

Compiled languages like Go and Rust are my new default for projects on the backend, typescript with strict typing on for the frontend, and I foresee the popularity growing the more LLM use grows. The moment you let an LLM loose in a Javascript/Python codebase everything goes off the rails.

Re: When AI writes the software, who verifies it?

#218

Post by thorn »

I don’t think many people are interested in producing 100% correct code. I saw this at big companies and small startups. It is all the same: ship feature asap before competitors. Writing correct code is almost always punished indirectly in the way they only praise the feature delivering heroes that got promoted. Nobody got promoted for preventing bugs.

Maybe in some other circles it is not like that, but I am sure that 90% of industry measures output in the amount of value produced and correct code is not the value you can show to the stockholders.

It is sad state of affairs dictated by profit seeking way of life (capitalism).

Re: When AI writes the software, who verifies it?

#219

Post by Karrot_Kream »

pmontra wrote: post #199
WhyNotHugo wrote: post #180

Earlier quoted context omitted.

This is why you write the tests first and then the code. Especially when fixing bugs, since you can be sure that the test properly fails when the bug is present.

When fixing bugs, yes. When designing an app not so much because you realize many unexpected things while writing the code and seeing how it behaves. Often the original test code would test something that is never built. It's obvious for integration tests but it happens for tests of API calls and even for unit tests. One could start writing unit tests for a module or class and eventually realize that it must be imple…

Where I'm at currently (which may change) is that I lay down the foundation of the program and its initial tests first. That initial bit is completely manual. Then when I'm happy that the program is sufficiently "built up", I let the LLM go crazy. I still audit the tests though personally auditing tests is the part of programming I like the very least. This also largely preserves the initial architectural patterns that I set so it's just much easier to read LLM code.

In a team setting I try to do the same thing and invite team members to start writing the initial code by hand only. I suspect if an urgent deliverable comes up though, I will be flexible on some of my ideas.

Re: When AI writes the software, who verifies it?

#220

Post by hulitu »

codegladiator wrote: post #178
tbossanova wrote: post #173

Earlier quoted context omitted.

Once upon a time people advocated writing tests first…

once upon a time 'engineering' in software had some meaning attached to it... no other engineering profession would accept the standards(or rather their lack of) on which software engineering is running.

> no other engineering profession would accept the standards(or rather their lack of) on which software engineering is running.

I have bad news for you: they are pushing those "standards" (Agile, ASPICE) also in hardware and mechanical engineering.

The results can be seen already. Testing is expensive and this is the field where most savings can be implemented.

Post reply on HN