| ▲ | eloisant 4 days ago |
| If you truly think LLM are not useful tools for programming, you haven't tried the right tools. |
|
| ▲ | jeltz 4 days ago | parent | next [-] |
| That is not the same topic. LLMs are useful tools, and that is despite them producing fucking awful code. |
| |
| ▲ | Gigachad 4 days ago | parent [-] | | I would have agreed with you 6 months ago but things have changed rapidly. | | |
| ▲ | wizzwizz4 4 days ago | parent | next [-] | | People say this every 6 months. I've stopped even paying attention to it, because (A) the code quality remains below the floor, and (B) the people saying it continue to ignore all the other issues with LLM code generation. | | |
| ▲ | Zambyte 4 days ago | parent | next [-] | | Up until the last couple of months, I have treated LLMs as a supercharged stackoverflow. I would ask it questions on how to do something in a general sense, and then adapt the answer to my use case. Now, my entire programming flow does not even include an editor. The tools I use are: pi.dev to write and implement openspec specifications, herdr to manage many pi instances, and ollama to run qwen 3.8 27b on my single 7900 XTX. Writing good specifications is the key detail here. I will often iterate on a spec for hours until I am happy with it all of the details. Once I am happy with the spec, I can be quite confident that when I tell pi to apply the spec, the changes that I want will be done, and done how I want them, when I come back to check when it reports itself as done. The landscale is fundamentally different from what it was. Feel free to ignore it, but you can absolutely generate high quality code if you know what you're doing. | | |
| ▲ | panny 4 days ago | parent [-] | | >ollama to run qwen 3.8 27b Installed this recently to try it out. >pi.dev to write and implement openspec specifications, herdr to manage many pi instances Thanks for mentioning the tools you're using successfully. It seems like most people using LLMs are keen to keep their cards close to their chest. | | |
| ▲ | Zambyte 4 days ago | parent [-] | | No problem. I think it's less of people withholding information to have an advantage, and more people still not having settled on a workflow they like. Herdr is the most recent addition in my workflow as of only a few days ago, but it directly solves problems I have been having (juggling tons of terminals, even with my tiling wm has been a little unwieldy). The rest I've pretty much settled into for a while now. | | |
| ▲ | Zambyte 3 days ago | parent [-] | | The other tool I wanted to throw out there is voxtype (plus wtype). I've been looking for a good, global, local dictation solution for wayland for a while now, and finally landed on this one. It's great for rambling details that pi+qwen can then convert into concrete openspec specifications. |
|
|
| |
| ▲ | kuboble 4 days ago | parent | prev [-] | | N=1 and might be a raw skill issue on my end. But I all but stopped writing code 13 months ago. At the beginning the code was often bad. In the last 6 months alone I had received more praise from my customers for excellent work than ever before. |
| |
| ▲ | jeltz 4 days ago | parent | prev [-] | | Not sure what I can say but the LLMs simply do not write good code without tons of handholding. As a C developer most LLMed patches I have seen the last couple of months have been awful and the few good ones I know from the author themselves that they did a ton of iteration and/or manual cleanup. Maybe they are less bad at writing other languages. | | |
| ▲ | Gigachad 4 days ago | parent [-] | | At least what I have seen in Ruby and Typescript, they are excellent at doing what you asked for. But if what you asked for is stupid they will happily make it happen. They don’t make normal mistakes like typos and they aren’t lazy so things like tests and checking error cases is usually done. |
|
|
|
|
| ▲ | roblabla 4 days ago | parent | prev [-] |
| I tried a lot of tools. Claude code, deepseek with kilocode and OMP, codex... I still use claude quite a bit. But frankly, all of them produce some absolutely godawful code. Review load went way up with AI, and it's not just the volume that caused it, but also the quality. It's extremely verbose, hard to read, often repeats code instead of factoring it into reusable components. And yes, sometimes it's also buggy. Except now, you have to debug a problem that's in code you didn't write yourself, and is awful to read. LLM is incredibly valuable for debugging complex problems, codebase exploration, and planning large changes. But the writing code part itself, I find, LLMs are just not very good at it yet. |
| |
| ▲ | user43928 4 days ago | parent | next [-] | | I don't have to debug anything. Vaguely telling the agent what the issue is and what behavior I expect solves the issue with a fraction of the effort. Some claim that the tech debt only keeps increasing and that the result will be unmaintainable. This is not my experience, and I don't think it is theirs either. These claims are often entirely speculative. | | |
| ▲ | RHSeeger 4 days ago | parent | next [-] | | I, and I think most experienced developers, can recognize the type of code that incurs a maintenance cost down the line; that will make adding new code take longer. And AI writes such code "relatively" frequently. I love having the AI to write code, but I find it extremely important to review it - to make sure that it's correct, understandable, and not going to be a problem later. | | |
| ▲ | user43928 4 days ago | parent [-] | | I find it unnecessary for most non-critical code, such as client applications. I doubt that any supposed future extra effort for the AI to add new code is remotely comparable to the upfront effort of you reviewing the code manually. I know that this is the case today for native mobile apps, and I speak from hundreds of hours of experience over the last four months on such a project where I stopped reviewing the code. We are already here today, and this balance is only going to further shift to the point where it is obvious that the hands-on approach is no longer competitive. | | |
| ▲ | RHSeeger 4 days ago | parent [-] | | Everything about what you're said strikes me as sounding like "I don't bother wearing a seatbelt, because my experience is that I don't get in accidents" .. and also "I don't write automated tests, because I already hand tested my code and it works". And neither one of those statements is very convincing to me. | | |
| ▲ | user43928 4 days ago | parent [-] | | And what you said strikes me as speculation not based on actual experience in using AI in this way, with a healthy dose of condescension added. Anyway, I think we shared our viewpoints, and neither of us is going to change their mind until either my project fails spectacularly, or you change your approach in the future to use AI more autonomously. |
|
|
| |
| ▲ | roblabla 4 days ago | parent | prev [-] | | I've had bugs the agents can't fix or figure out. Sometimes those involve third-party, proprietary, broken code (read: Windows APIs). Sometimes they just involve complex deployment situation on the client code (I work on desktop apps) where the agent can't figure out what's wrong/makes wrong assumptions/goes nowhere. Sometimes the agent is just very dumb and tunnels vision on the wrong fix. FWIW, I've also had bugs the agent fixed that I probably never would've figured out without LLMs - LLMs are definitely useful! But I need to keep understanding how the code works so I can take over the reigns when the LLM fails. |
| |
| ▲ | api 4 days ago | parent | prev [-] | | I’ve had some luck prompting them to be concise, both in writing and in code, and with code doing an approach where they get it working, write tons of tests, and then refactor for conciseness and readability. All the tests prevent regressions doing this. Without such prompting and a conciseness and clarity pass you get a slop grenade. They overall work better with tests, and Rust is a great language for them. Overall they do better with lots of walls and alarms that go off if they mess up. I don’t need nearly as much of this, can mentally simulate it, which is a good “are we superintelligence yet” reality check. Still not even as good as my wet meat brain. But impressive given what was possible even two years ago! The result is still not as clean as a good programmer but it’s better than the slop grenade you get first pass. |
|
