|
| ▲ | dools 6 hours ago | parent | next [-] |
| I've built 4 pretty novel features where the LLM didn't know how to solve the problem, but with design/decision input from me was able to implement it. Between the two of us it was done, I would estimate, 10 - 20 times faster in terms of man hours than the same implementation would have taken without the use of LLMs. Like it's team level productivity from a single developer. In my case it was done infinity times faster because I just wouldn't have done these things, it would have been cost-prohibitive. |
|
| ▲ | simonw 8 hours ago | parent | prev | next [-] |
| > But if you are doing things that are not well represented in publicly available code, or in unusual languages, then LLMs are not great currently. Have you tried since November 2025? |
| |
| ▲ | what 8 hours ago | parent | next [-] | | >have you tried since $date You guys have been saying that every few months. | | |
| ▲ | simonw 8 hours ago | parent [-] | | And you guys have been consistently replying with that exact same comment. | | |
| ▲ | dools 6 hours ago | parent | next [-] | | Have you been consistently replying with the same answer to that comment? Or have you genuinely tried using coding agents? | |
| ▲ | what 4 hours ago | parent | prev [-] | | Maybe because not everyone works on trivial shit and it still doesn’t work for them? | | |
|
| |
| ▲ | ofjcihen 8 hours ago | parent | prev [-] | | They did get better around that time but there are some things that they are legitimately bad at for now. |
|
|
| ▲ | empty_set35204 7 hours ago | parent | prev [-] |
| For what it's worth, engineers at proprietary trading firms are finding that they can get substantial productivity boosts by using LLMs and it'd be hard to find a domain that's less represented in the training data. Does definitely require more steering than if you're churning out slop apps/websites though. |
