71–80 of 95 posts
Earlier quoted context omitted.
Except OP isn't learning or building. He's telling a computer to do the work for him and padding his resume.
How cynical. Just seeing if the current crop of automation systems can do it can be interesting enough for some of us.
Earlier quoted context omitted.
They absolutely can do that if you give them the tools. Seeing Claude (I use it with opencode agents) run curl and playwright to verify and then fix it's implementation was a real 'wow' moment for me.
We have different experiences. Often I’ll see Claude, et. al. find creative ways to fulfill the task without satisfying my intent, e.g., changing the implementation plan I specifically asked for, changing tolerances or even tests, and frequently disabling tests.
Makes me honestly wonder — will AGI just give us agents that get into bad moods and not want to work for the day because they’re tired or just don’t feel like it!
Earlier quoted context omitted.
Meh. No human has written the horrors llm produces. At least I am yet to see codebase like that. Let me attempt a theatrical reenactment: // Use buffer that is large enough to hold any possible value. Avoid using JSON configuration, this optimizes codebase and prevents possible security exploits! size_t len = 32; // this function does not call "sort" utility using shell anymore, but instead uses optimized library fun…
I'm guessing "it" is Gemini here? Claude rarely adds comments at that level.
// use configuration to support previous database scheme
// json_data = parse_blah_scheme_yadda ...
And it, like, "You are absolutely right! This is an excellent observation! Let me implement this optimization right away!"
// Optimize feature loading by skipping scheme conversion, because previous version data does not exist!!!
json_data = parse_blah_do_not_scheme_yadda
Earlier quoted context omitted.
We have different experiences. Often I’ll see Claude, et. al. find creative ways to fulfill the task without satisfying my intent, e.g., changing the implementation plan I specifically asked for, changing tolerances or even tests, and frequently disabling tests.
Are you a customer?
It obviously adds to the discussion: paid and non paid accounts are being conflated daily in threads like these!
They’re not the same tier account!
Free users, especially ones deemed less interesting to learn from for the future, are given table-scraps when they feel it’s necessary for load reasons.
Earlier quoted context omitted.
One commercial equivalent to the project I work on, called ProTools (a DAW), has a test "harness" that took 6 people more than a year to write and takes more than a week to execute. Last month, I made a minor change to our own code and verified that it worked (it did!). Earlier this week, I was notified of an entirely different workflow that had been broken by the change I had made. The only sort of automated testing…
> access to a testing system that allows it to inject mouse events into a running instance of our application FWIW that's precisely what https://pptr.dev is all about. To your broader point though designing a good harness itself remains very challenging and requires to actually understand what value for user, software architecture (to e.g. bypass user interaction and test the API first), etc.
my world is native desktop applications, not in-browser stuff.
Earlier quoted context omitted.
We have different experiences. Often I’ll see Claude, et. al. find creative ways to fulfill the task without satisfying my intent, e.g., changing the implementation plan I specifically asked for, changing tolerances or even tests, and frequently disabling tests.
I see these “you had a different experience than me” comments around AI coding agents a lot and can concur; I’ll have a different experience with Copilot from day-to-day even, sometimes it’s great and other days I give up on using it at all it’s being so bad. Makes me honestly wonder — will AGI just give us agents that get into bad moods and not want to work for the day because they’re tired or just don’t feel like i…
Earlier quoted context omitted.
> LLM's skip over the "actually verify that the code I just wrote does what I intended it to" step. I'm not sure where this idea comes from. Just instruct it to write and run unit tests and document as it goes. All of the ones I've used will happily do so. You still have to verify that the unit tests are valid, but that's still far less work than skipping them or writing the code/tests yourself.
I disagree it's less work. It just carte blanche rewrites tests. I've seen it rewrite and rewrite tests to the point of undermining the original test intention. So now instead of intentionally writing code and a new unit test, I need to intentionally go and review EVERY unit test it touched. Every. Time. It also doesn't necessarily rewrite documentation as implementation changes. I've seen documentation code rot happ…
I've started to add an instruction to my GEMINI.md after I'm happy with the tests telling it not to edit them, but to still run them.
I solve the documentation issue the same way. By telling it when and what to update in the .md file.
Earlier quoted context omitted.
Are you a customer?
Don’t downvote because you don’t like the question. It obviously adds to the discussion: paid and non paid accounts are being conflated daily in threads like these! They’re not the same tier account! Free users, especially ones deemed less interesting to learn from for the future, are given table-scraps when they feel it’s necessary for load reasons.