| ▲ | will__ness 11 hours ago |
| > But there are serious limits. [Your coding agent] will lie to you, they don't really understand things, and they often generate bad code. I think that really high quality code can be created via coding agents. Not in one prompt, but instead an orchestration of planning, implementing, validating, and reviewing. Its still engineering work. The code still matters. Its just a different tool to write the code. I'd compare the difference between manually coding and operating a coding agent to the difference between a handsaw and a chainsaw - the end result is the same but the method is very different. |
|
| ▲ | acedTrex 10 hours ago | parent | next [-] |
| > the end result is the same but the method is very different. I dont think anyone really cares at all about LLM code that is the exact same end result as the hand written version. It's just in reality the LLM version is almost never the same as the hand written version, it's orders of magnitude worse. |
| |
| ▲ | elzbardico 10 hours ago | parent | next [-] | | But a lot of people don't think like this, and we must come to the unavoidable conclusion that the LLM code is better than what they are used to, be their own code, or from their colleagues. | |
| ▲ | nubg 10 hours ago | parent | prev [-] | | Speak for yourself. | | |
| ▲ | acedTrex 10 hours ago | parent [-] | | I mean yes, i am speaking for myself. I am drowning in mountains of LLM slop patches lol. I WISH people were using LLMs as "just another tool to generate code, akin to a vim vs emacs discussion." | | |
| ▲ | SchemaLoad 9 hours ago | parent | next [-] | | I'm so sick of being dumped 1000 line diffs from coworkers who have generated whole internal libraries that handle very complicated operations that are difficult to verify. And you just know they spend almost no time properly testing and verifying since it was zero effort to generate it all in the first place. | |
| ▲ | simplify 8 hours ago | parent | prev [-] | | LLMs are an amplifier. The great get greater, and the lazier get lazier. | | |
| ▲ | Madmallard 2 hours ago | parent [-] | | Considering the seeming increasing frequency of high severity bugs happening at FAANG companies in the last year I think perhaps The great getting greater is not actually the case. |
|
|
|
|
|
| ▲ | nielsbot 9 hours ago | parent | prev | next [-] |
| > Not in one prompt, but instead an orchestration of planning, implementing, validating, and reviewing Lots of times I could just write it myself and be done with it |
| |
| ▲ | fartfeatures 9 hours ago | parent [-] | | Sure and lots of times I can walk places. That doesn't mean bikes, cars, trains and planes aren't incredibly useful. They let me achieve things I can't in other ways for example transporting cargo without a team of people to help me. Just like AI coding. | | |
| ▲ | trollbridge 8 hours ago | parent | next [-] | | Yet replacing walking with cars is often cited as one of the reasons for many of society's ills. | |
| ▲ | nielsbot 9 hours ago | parent | prev | next [-] | | Maybe your analogy holds if driving and walking took the same amount of time. Plus "planning, implementing, validating, and reviewing" would be a bit like walking anyway in your analogy. | |
| ▲ | worksonmine 5 hours ago | parent | prev [-] | | Would you still use your car if you ended up in the wrong destination half the time? | | |
| ▲ | XenophileJKO 5 hours ago | parent | next [-] | | Yes, because I can drive to the other end of the state in an afternoon. Then if I get lost, I can just course correct. | | |
| ▲ | makapuf 4 hours ago | parent | next [-] | | Generating lots of pollution, cost, jams, noise and accidents globally. Not all cities need to be made for cars, right tool for the job etc. | |
| ▲ | worksonmine 2 hours ago | parent | prev [-] | | Have fun getting stuck in a loop when it insists your destination exists in a place it doesn't. |
| |
| ▲ | stevenhuang 34 minutes ago | parent | prev [-] | | Would you use your car if you ended up in the right destination 100% - epsilon of the time? Yes, you would. Or do you suppose this is the best AI will ever get? |
|
|
|
|
| ▲ | storystarling 3 hours ago | parent | prev | next [-] |
| The practical limit is the latency and inference cost. A full planning and validation loop burns a lot of tokens, and waiting for that cycle breaks flow compared to just writing the code. |
|
| ▲ | solomatov 10 hours ago | parent | prev | next [-] |
| >I think that really high quality code can be created via coding agents. Not in one prompt, but instead an orchestration of planning, implementing, validating, and reviewing. Do you have any advice to share (or resources)? Have you experienced it yourself? |
|
| ▲ | mbesto 9 hours ago | parent | prev [-] |
| > high quality code What does high quality code look like? > The code still matters. How so? |
