Hacker Newsnew | past | comments | ask | show | jobs | submit | vorticalbox's commentslogin

one thing that aways slowed me down was writing jsdocs and testing.

Now i can write one example of a pass and then get codex to read the code and write a test for all the branches in that section saves time as it can type a lot faster than i can and its mostly copying the example i already have but changing the input to hit all the branches.


> let's have LLMs check our code for correctness

Lmao. Rofl even.

(Testing is the one thing you would never outsource to AI.)


Outsourcing testing to AI makes perfect sense if you assume that tests exist out of an obligation to meet some code coverage requirements, rather than to ensure correctness. Often I'll write a module and a few tests that cover its functionality, only for CI to complain that line coverage has decreased and reject my merge! AI to the rescue! A perfect job for a bullshit generator.

outsourcing testing the AI also gets its code to be connected to deterministic results, and show let the agent interact with the code to speculate expectations and check them against the actual code.

it could still speculate wrong things, but it wont speculate that the code is supposed to crash on the first line of code


> Testing is the one thing you would never outsource to AI

That's not really true.

Making the AI write the code, the test, and the review of itself within the same session is YOLO.

There's a ton of scaffolding in testing that can be easily automated.

When I ask the AI to test, I typically provide a lot of equivalence classes.

And the AI still surprises me with finding more.

On the other hand, it's equally excellent at saying "it tested", and when you look at the tests, they can be extremely shallow. Or they can be fairly many unit tests of certain parts of the code, but when you run the whole program, it just breaks.

The most valuable testing when programming with AI (generated by AI, or otherwise) are near-realistic integration tests. That's true for human programmers, but we take for granted that casual use of the program we make as we develop it constitutes as a poor man's test. When people who generally don't write tests start using AI, there's just nothing but fingers crossed.

I'd rather say: If there's one thing you would never outsource to AI, it's final QA.


Yep. I have had had success getting AI to write tests. They all needed review, but still a massive speed up for me.

It made about 2 mistakes in over 100 tests, and the coverage of the tests was higher than I would have attempted.

So about 2 hours of work instead of 1 or 2 days of boring effort avoided and a better outcome.


> (Testing is the one thing you would never outsource to AI.)

I would rephrase that as "all LLMs, no matter how many you use, are only as good as one single pair of eyes".

If you're a one-person team and have no capital to spend on a proper test team, set the AI at it. If you're a megacorp with 10k full time QA testers, the AI probably isn't going to catch anything novel that the rest of them didn't, but it's cheap enough you can have it work through everything to make sure you have, actually, worked through everything.


You don't use the LLM to check your code for correctness; you use the LLM to generate tests to exercise code paths, and verify that they do exercise those code paths.

And that test will check the code paths are run.

That doesn't tell you that the code is correct. It tells you that the branching code can reach all the branches. That isn't very useful.


can the agent not simply be instructed to save the "why" in the commit message?

I have started using openspec for this. I find it works far better to have a proposal and a list of tasks the ai stays more focused.

https://openspec.dev/


I have been using glm-4.7 a bunch today and it’s actually pretty good.

I set up a bot on 4claw and although it’s kinda slow, it took twenty minutes to load 3 subs and 5 posts from each then comment on interesting ones.

It actually managed to correctly use the api via curl though at one point it got a little stuck as it didn’t escape its json.

I’m going to run it for a few days but very impressed so for for such a small model.


you can check the github https://github.com/cryptomator/ios


Even if I had the skills to confirm the code is secure, how could I know that this is the code running on my phone, without also having the skills to build and deploy it from source?


Also, you need to make sure that the installation process does not insert a backdoor into the code you built from source.



This is like opencode, it’s seems all the coding agents are converging on the same features.


it also said to have "different ages for different services" so the fact you have a debit/credit card to pay is more than enough to prove you at least 16.

this will be interesting to watch i just wish i weren't caught in the net.


That's never been true in the UK? You don't have to be 16 to get a debit card, and having one isn't proof of any age. (For example, Barclays gave me my first debit card when I was 13, many years ago.)


There are debit cards in the UK marketed for down to 6 years old. Granted the accounts are linked to a parent.


After I have wrote a feature and I’m in the ironing out bug stage this is where I like the agents do a lot of the grunt work, I don’t want to write jsdocs, or fix this lint issue.

I have also started it in writing tests.

I will write the first test the “good path” it can copy this and tweak the inputs to trigger all the branches far faster than I can.


I like opencode for the fact I can switch between build and plan mode just by pressing tab.


Isn't it the same in base claude-code?


Yes.


Its shift-tab in Claude Code, fyi


yes [0]

> The Rust implementation is now the maintained Codex CLI and serves as the default experience

[0] https://github.com/openai/codex/tree/main/codex-rs#whats-new...


They should switch to a native installer then. Quite confusing



Yeah I'm out here installing a billion node things to have codex hack on my python app. Def gonna look into a standalone rust binary.


They're leveraging the (relative) ubiquity of npm amongst developers.


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

Search: