News for hackers. Stuff that matters.
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by wtetzner on Thursday May 15, 2025 @07:36PM (#44000420)
Sure, you can probably get better at it, but is it really worth the effort over just getting better at programming?
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by kgeist on Thursday May 15, 2025 @08:00PM (#44000537)
When I have to explain what I want, and review it, and correct it, in as many words as it would take me to write the code myself (+ good autocomplete), then it's the same programming as before but with extra steps. So far I've found that LLMs are good as a starting point, when you have no idea where to even start (not only for coding, but in general). Everything else... feels less productive so far.
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by cyral on Thursday May 15, 2025 @07:46PM (#44000470)
You can do both
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by cheema33 on Thursday May 15, 2025 @08:34PM (#44000733)
If you are going to race a fighter jet, and you are on a bicycle, exercising more and eating right will not help. You have to use a better tool.

A good programmer with AI tools will run circles around a good programmer without AI tools.

Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by mattbuilds on Friday May 16, 2025 @12:12AM (#44001778)
Got any evidence on that or is it just “vibes”? I have my doubts that AI tools are helping good programmers much at all, forget about “running circles” around others.
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by hdjrudni on Friday May 16, 2025 @12:50AM (#44001939)
I don't know about "running circles" but they seem to help with mundane/repetitive tasks. As in, LLMs provide greater than zero benefit, even to experienced programmers.

My success ratio still isn't very high, but for certain easy tasks, I'll let an LLM take a crack at it.

Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by candiddevmike on Thursday May 15, 2025 @09:12PM (#44000916)
What does that even mean? How do you even quantify that?
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by Groxx on Thursday May 15, 2025 @09:38PM (#44001058)
With vibes, mostly
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by TeMPOraL on Friday May 16, 2025 @02:57AM (#44002504)
Like everything in software engineering. It's not like there's much science in any of the issues of practice programmers routinely debate.
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by HDThoreaun on Friday May 16, 2025 @08:47AM (#44004820)
My teams velocity before and after adding AI coding to our stack
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by goatlover on Thursday May 15, 2025 @10:06PM (#44001217)
Citation needed for your second sentence. This is the problem with AI hype cycles. Lots of outstanding claims, a lot less actual evidence supporting those claims. Lot of anecdotes though. Maybe the LLMs are in a loop recursively promoting themselves for that sweet venture funding.
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by ebiester on Friday May 16, 2025 @09:37AM (#44005384)
Studies take time. https://www.microsoft.com/en-us/research/wp-content/uploads/... is the first one from Microsoft. But it goes back to gains coming as people become more skilled.
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by jsight on Friday May 16, 2025 @12:42AM (#44001903)
To be fair, that's also what a lot of us used to say about IDEs. In reality, plenty of folks just turned vim into a fighter jet and did just as well without super-heavyweight llms.

I'm not totally convinced that we won't see a similar effect here, with some really competitive coders 100% eschewing LLMs and still doing as well as the best that use them.

Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by TeMPOraL on Friday May 16, 2025 @02:55AM (#44002501)
> In reality, plenty of folks just turned vim into a fighter jet and did just as well without super-heavyweight llms.

No, they didn't.

You can get vim and Emacs on par with IDEs[0] somewhat easily thanks to Language Server Protocol. You can't turn them into "fighter jets" without "super-heavyweight LLMs" because that's literally what, per GP, makes an editor/IDE a fighter jet. Yes, Emacs has packages for LLM integration, and presumably so does Vim, but the whole "fighter jet vs. bicycle" is entirely about SOTA LLMs being involved or not.

--

[0] - On par wrt. project-level features IDEs excel at; both editors of course have other aspects that none of the IDEs ever come close to.

Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by jsight on Friday May 16, 2025 @05:21PM (#44009906)
Honestly, that is a really fair counterpoint. I've been playing with neovim lately and it really feels a lot like some of the earlier IDEs that I used to use but with more modern power and tremendous speed.

Maybe we will all use LLMs one day in neovim too. :)

Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by drittich on Friday May 16, 2025 @07:37AM (#44004139)
Perhaps that's a false dichotomy?
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by wtetzner on Friday May 16, 2025 @09:45PM (#44011421)
Kinda, but there's always an opportunity cost.
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by ebiester on Friday May 16, 2025 @09:30AM (#44005306)
Yes, not because you will be able to solve harder problems, but because you will be able to more quickly solve easier problems which will free up more time to get better at programming, as well as get better at the domain in which you're programming. (That is, talking with your users.)
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by wtetzner on Saturday May 17, 2025 @03:32PM (#44016424)
> because you will be able to more quickly solve easier problems which will free up more time to get better at programming

I'm not really convinced by this. Easy problems rarely take up much of my time.