| ▲ | palata a day ago |
| I agree that it's an opportunity to "do it the old way", as a way to preserve the skill. I actually would like to do that regularly, like half a day every week or something. But I find it difficult to motivate it from the "productivity" angle. Like if I work for a day without an LLM today, it feels like I could go skiing instead, and the LLM will do what I would have done today in 10min tomorrow... |
|
| ▲ | billbuild a day ago | parent | next [-] |
| Seriously, if the LLM was down and a dev submitted 10 PRs, I think it would raise some good/bad curiosity from the team with where things stands today. |
| |
| ▲ | voakbasda a day ago | parent | next [-] | | I have couple dozen branches in flight at any time. A snow day is the perfect opportunity to catch up and get those pushed. | |
| ▲ | trollbridge a day ago | parent | prev [-] | | I'd be busy yelling at my Mac and trying to get things down with 3.8b-27b, but I'd still be getting things done. |
|
|
| ▲ | Jtarii a day ago | parent | prev | next [-] |
| And the LLMs of 5 years from now will do what current LLMs do in a day in 1 minute. |
| |
| ▲ | ionwake a day ago | parent | next [-] | | just want to remind HN that it was as little as a year when I mentioned I used LLMs to do all my coding, totally hands off and people here found it a curiosity. One year later and its madness to even contemplate coding manually. Im not complaining Im just pointing out how quickly the overton window is shifting. | | |
| ▲ | ric2b a day ago | parent | next [-] | | It's not the overton window, it's the capabilities of the models that have changed significantly in 1 year. | | |
| ▲ | ionwake a day ago | parent [-] | | I disagree. For me I had already been using hands off ocding for about 2 years by that point. | | |
| ▲ | palata a day ago | parent [-] | | > For me Obviously that's not the case for everybody. 3 years ago, LLMs were very far from producing the quality of code I wanted in my domain. | | |
| ▲ | ionwake 24 minutes ago | parent [-] | | Yes but I contend that was lack of time or effort dedicated to custom harnesses but that the tech was always there I jsut feel the HN crowd is very “ai was crap before but suddenly now it’s good” I’ve always noticed a linear progression in a way since ChatGPT 3 |
|
|
| |
| ▲ | cstever a day ago | parent | prev | next [-] | | Hey will you share your workflow and how you get LLMs to build correct things for you (or inspite of you)? | | |
| ▲ | alex43578 a day ago | parent | next [-] | | If you’re using the latest models( Opus/Fable/Astra/ maybe Sol) and the default harness, along with a little guidance against the worst tendencies like over-writing tests, you really shouldn’t be getting the wrong things built. Like a coworker, you can’t throw it blind into a monster codebase without some guidance, but otherwise the latest models genuinely just work TM. | |
| ▲ | gibspaulding a day ago | parent | prev [-] | | Testing, testing, and more testing. In the project I'm working on right now, about 2/3 of the code is in one way or another related to testing. As a human coder, I'd never spend that much time on building test harnesses, automating regressions, writing unit tests, etc, but it's cheap when you can have a robot do it. | | |
| ▲ | usr1106 a day ago | parent [-] | | So you assume code written by the agent canno be trusted? But how comes you are trusting the tests? | | |
| ▲ | alemanek a day ago | parent | next [-] | | At my work we still have a QA dept that runs the manual test suites before each release. We have also automated almost all of those manual tests and they gate every merge to mainline. Things are still found but normally it is a new test case or an edge condition we don’t have an automated test for. The ever growing e2e suite has reduced the amount of regressions pretty drastically. EDIT: I forgot to note that automated e2e tests were always the answer to improving quality. AI has just made it cheap to have several layers of test coverage. | |
| ▲ | voakbasda a day ago | parent | prev | next [-] | | To start, you make it a rule that every test must pass with the fix being tested, and it must fail if the fix is missing. | |
| ▲ | BonerWiener a day ago | parent | prev [-] | | You of course use another AI to test your tests, have you been living under a rock? /s | | |
| ▲ | eocjiwnceidj a day ago | parent [-] | | How are these /s posts even allowed? You contributed nothing to the conversation other than noise. | | |
|
|
|
| |
| ▲ | soon_to_be_sb a day ago | parent | prev | next [-] | | > One year later and its madness to even contemplate coding manually... Seriously, why do people assume that what they feel should be how everyone else should be feeling? | | |
| ▲ | edoceo a day ago | parent [-] | | I think it's called Normative Cognition or something. Like: I'm normal, and I do X. Therefore other normal people will also do X. It's the basis for in-group/out-group. We're all normal and they are not. (for some definition of normal). |
| |
| ▲ | BodyCulture a day ago | parent | prev | next [-] | | How are you handling all the errors that are hidden in code you can not understand? | | | |
| ▲ | Betelbuddy a day ago | parent | prev | next [-] | | You give it time....the same way Technical debt is code you chose not to clean up....your Vibe Debt for code you never understood in the first place... will come through. | | |
| ▲ | ionwake a day ago | parent [-] | | I dont think so man, it havent really had any issues that Ive noticed | | |
| |
| ▲ | cgio a day ago | parent | prev | next [-] | | I am sure it’s all so good that these incidents should not take more than 5 minutes to resolve. Don’t get me wrong, I am one of the people who would look at you suspiciously a year ago and only in the last year “saw the light”. You were ahead. But that doesn’t mean that at some point you will not overshoot. What we witness today we haven’t witnessed in some time. People also made horrible software but they enriched it with hole plugging hacks that made it run, mostly. AI may build better software but who is plugging the holes. At least today no one. In 1 or 5 years maybe AI. In the meantime, we need to plug some holes and they are not as easy to spot when we are not the ones who left them there. | |
| ▲ | recursive a day ago | parent | prev | next [-] | | Madness? I didn't think we'd gone that far... | |
| ▲ | TZubiri 21 hours ago | parent | prev | next [-] | | So either I am mad or you are all mad, time will tell | |
| ▲ | dutchiesareok a day ago | parent | prev | next [-] | | "Overton window"? It's just developers being obtuse, short-sighted and slow. It was obvious in 2023 and it is obvious now yet we still have people in denial even today. These people need AI to take over the world and threatening them with eternal suffering before they will change their minds even a bit. | | |
| ▲ | jenniferhooley a day ago | parent | next [-] | | May I ask why you care so much? Some people like hand-coding, they are free to do whatever they want, stop being so weirdly angry and controlling about what people do/how they do it. | |
| ▲ | palata a day ago | parent | prev [-] | | "It was obvious then, and it is obvious now: I am always right, I can predict the future, whoever disagrees with me is wrong" | | |
| ▲ | 12_throw_away 19 hours ago | parent [-] | | Don't forget the "it is inevitable" and "people who disagree with me will be punished and humiliated" | | |
| ▲ | ifwinterco 3 hours ago | parent [-] | | Honestly I would kind of love to have this kind of certainty, sounds like it would be fun to be that sure of myself. Living with the bitterness and vindictiveness that seems to come with it would be less fun though |
|
|
| |
| ▲ | sehw a day ago | parent | prev [-] | | [flagged] |
| |
| ▲ | palata a day ago | parent | prev | next [-] | | Yes, but my company does not pay me every 5 years. I don't know about you, but if I wait 5 years, I won't get a salary in the meantime. If I wait until tomorrow, though, my company won't see the difference. | | |
| ▲ | Jtarii a day ago | parent [-] | | Sure, but depending on what your job is it can make the work feel even more meaningless than it was prior to LLMs. All the work most people are doing it just going to be Ctrl+A deleted and replaced with someone else's LLM slop using Opus 8 in an afternoon. All the shit people are building right now just feel ephemeral, like its going to float away on a breeze. | | |
| ▲ | palata a day ago | parent | next [-] | | Well it's getting philosophical. Even before AI, I would argue that the vast majority of software was meaningless. Actually the most successful software on Earth is hurting society and the environment, in exchange for profit for a few humans. I don't know any software engineer who can say "if I was not doing what I do, society would get a little worse". | | |
| ▲ | ifwinterco 3 hours ago | parent | next [-] | | Also even before LLMs, a lot of software was already kind of semi-disposable. You write an app, maintain it for a few years, then once the code starts getting a bit old and messy developers start advocating for writing a new version from scratch in the latest shiny language/framework and rinse/repeat. That was already completely normal in the 2010s before LLMs in my experience, most developers don't want to maintain other people's old code and will try and manoeuvre politically to avoid it | |
| ▲ | dutchiesareok a day ago | parent | prev | next [-] | | I console myself that while the products we make are useless and probably even harmful the activity itself just represents the world Geist familiarizing itself with computation and its possibilities and thus growing richer in the process. In the worst case.. sometimes you learn what's best by experiencing what's not. | | | |
| ▲ | edoceo a day ago | parent | prev | next [-] | | The folk keeping Wikipedia running? | | |
| ▲ | palata 20 hours ago | parent [-] | | Maybe not part of the "vast majority"? The idea of "the vast majority" is that it's not "everybody". | | |
| ▲ | edoceo 17 hours ago | parent [-] | | Of course not. I was responding to your second paragraph. | | |
| ▲ | palata 16 hours ago | parent [-] | | Oh, I see. Well I don't know any software engineer who works at Wikipedia :-). |
|
|
| |
| ▲ | tosapple a day ago | parent | prev [-] | | sad. | | |
| ▲ | palata a day ago | parent [-] | | Well it's not just software engineers. The majority of people in developed countries work in offices. And when you work in an office, it's highly likely that your work is not fundamentally useful. | | |
| ▲ | utternerd 21 hours ago | parent [-] | | > And when you work in an office, it's highly likely that your work is not fundamentally useful. This seems wildly inaccurate. | | |
| ▲ | palata 20 hours ago | parent [-] | | Well, for some definition of useful of course. If you find it wildly inaccurate, maybe you don't have the definition that matches :-). |
|
|
|
| |
| ▲ | ifwinterco a day ago | parent | prev [-] | | You might be right in the end, but the middle of a massive outage probably at least somewhat exacerbated by LLMs, being debugged by (presumably) human software engineers is kind of a weird time to make this point |
|
| |
| ▲ | ponector 21 hours ago | parent | prev [-] | | Like to burn billions of tokens? For sure! |
|
|
| ▲ | samiv a day ago | parent | prev | next [-] |
| Which is the way it should be if we were to share the fruits of our labour more evenly in society. Of course in practice the lions share of the product gains go to the capital class and the while they suck the surplus employees and the remaining workers have to carry the burden of supporting the ones now sidelined. |
|
| ▲ | iknowSFR a day ago | parent | prev | next [-] |
| Once you use a cheat code like “how do you turn this on?” It’s really difficult to finish the game without it. |
|
| ▲ | trollbridge a day ago | parent | prev | next [-] |
| Snow day / skiing? Since this has affected our customers, and they're asking us for help, it means I was up all last night. Ironically, I also had a change window last night to make some configuration changes to improve site reliability. It was a little challenging to get customer approval for both the cost & downtime for this. Let's just say... this will be a much more fun conversation to have next week, and for the account manager to have. "Yes, we'e proactively improved your reliablity, and here's why you were very smart to approve it and pay for it." |
|
| ▲ | reaperducer a day ago | parent | prev [-] |
| it feels like I could go skiing instead, and the LLM will do what I would have done today in 10min tomorrow... You sound self-employed. |
| |
| ▲ | palata a day ago | parent [-] | | Or during that day where the LLM is down and I pretend to work, I feel like I am wasting my time for no reason. |
|
