Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: Do you have any evidence that agentic coding works?

news.ycombinator.com

Post reply on HN
Print view View original

31–40 of 478 posts

Re: Ask HN: Do you have any evidence that agentic coding works?

#31

Post by highspeedbus »

Honestly, I only use coding agents when I feel too lazy to type lots of boilerplate code.

As in "Please write just this one for me". Even still, I take care to review each line produced. The key is making small changes at a time.

Otherwise, I type out and think about everything being done when in ‘Flow State’. I don't like the feeling of vibe coding for long periods. It completely changes the way work is done, it takes away agency.

On a bit of a tangent, I can't get in Flow State when using agents. At least not as we usually define it.

Re: Ask HN: Do you have any evidence that agentic coding works?

#32

Post by terabytest »

linesofcode wrote: post #6

When you first began learning how to program were you building and shipping apps the next day? No. Agentic programming is a skill-set and a muscle you need to develop just like you did with coding in the past. Things didn’t just suddenly go downhill after an arbitrary tipping point - what happened is you hit a knowledge gap in the tooling and gave up. Reflect on what went wrong and use that knowledge next time you wo…

Your point is fair, but it rests on a major assumption I'd question: that the only limit lies with the user, and the tooling itself has none. What if it’s more like “you can’t squeeze blood from a stone”? That is, agentic coding may simply have no greater potential than what I've already tried. To be fair I haven't gone all the way in trying to make it work but, even if some minor workarounds exist, the full promise being hyped might not be realistically attainable.

Re: Ask HN: Do you have any evidence that agentic coding works?

#33

Post by CjHuber »

vessenes wrote: post #20

Yep, it works. Like anything getting the most out of these tools is its own (human) skill. With that in mind, a couple of comments - think of the coding agents as personalities with blind spots. A code review by all of them and a synthesis step is a good idea. In fact currently popular is the “rule of 5” which suggests you need the LLM to review five times, and to vary the level of review, e.g. bugs, architecture, st…

I still don't get what beads needs a daemon for, or a db. After a while of using 'bd --no-daemon --no-db' I was sick of it and switched to beans and my agents seem to be able to make use of it much better, on the one hand its directly editable by them as its just markdown, on the other hand the CLI still gives them structure and makes the thing queryable

Re: Ask HN: Do you have any evidence that agentic coding works?

#34

Post by fotcorn »

I used Claude Opus 4.5 inside Cursor to write RISC-V Vector/SIMD code. Specifically Depthwise Convolution and normal Convolution layers for a CNN.

I started out by letting it write a naive C version without intrinsic, and validated it against the PyTorch version.

Then I asked it (and two other models, Gemini 3.0 and GPT 5.1) to come up with some ideas on how to make it faster using SIMD vector instructions and write those down as markdown files.

Finally, I started the agent loop by giving Cursor those three markdown files, the naive C code and some more information on how to compile the code, and also an SSH command where it can upload the program and test it.

It then tested a few different variants, ran it on the target (RISC-V SBC, OrangePI RV2) to check if it improves runtime, and then continue from there. It did this 10 times, until it arrived at the final version.

The final code is very readable, and faster than any other library or compiler that I have found so far. I think the clear guardrails (output has to match exactly the reference output from PyTorch, performance must be better than before) makes this work very well.

Re: Ask HN: Do you have any evidence that agentic coding works?

#35

Post by monooso »

edude03 wrote: post #4

I have the same experience despite using claude every day. As an funny anecdote: Someone I know wrote the code and the unit tests for a new feature with an agent. The code was subtly wrong, fine, it happens, but worse the 30 or so tests they added added 10 minutes to the test run time and they all essentially amounted to `expect(true).to.be(true)` because the LLM had worked around the code not working in the tests

There was an article on HN last week (?) which described this exact behaviour in the newer models.

Older, less "capable", models would fail to accomplish a task. Newer models would cheat, and provide a worthless but apparently functional solution.

Hopefully someone with a larger context window than myself can recall the article in question.

Re: Ask HN: Do you have any evidence that agentic coding works?

#36

Post by rzmmm »

saikatsg wrote: post #26

> Scaling long-running autonomous coding https://news.ycombinator.com/item?id=46624541

I'm not sure OP is looking for evidence like this. There are many optimistic articles from people or organizations who are selling AI products, AI courses, or AI newsletters.

Re: Ask HN: Do you have any evidence that agentic coding works?

#37

Post by DustinBrett »

I've been having good results lately/finally with Opus 4.5 in Cursor. It still isn't one-shotting my entire task, but the 90% of the way it gets me is pretty close to what I wanted, which is better than in the past. I feel more confident in telling it to change things without it making it worse. I only use it at work so I can't share anything, but I can say I write less code by hand now that it's producing something acceptable.

For sysops stuff I have found it extremely useful, once it has MCP's into all relevant services, I use it as the first place I go to ask what is happening with something specific on the backend.

Re: Ask HN: Do you have any evidence that agentic coding works?

#38

Post by nathan_compton »

I think of coding agents more like "typing assistants" than programmers. If you know exactly what and how to do what you want, you can ask them to do it with clear instructions and save yourself the trouble of typing the code out.

Otherwise, they are bad.

Re: Ask HN: Do you have any evidence that agentic coding works?

#39

Post by pzo »

Gazoche wrote: post #10
koakuma-chan wrote: post #7

> The product has to work, but the code must also be high-quality. I think in most cases the speed at which AI can produce code outweighs technical debt, etc.

But the thing with debt is that it has to be paid eventually.

project also have to be paid off financially. We have been there before - startup used to go fast and break things so that once MVP is validated they slow down and fix things or even rewrite to new tech/architecture. No you can validate idea even faster with AI. And probably there is a lot of code that you write for one time or throw away internal tools etc.

Re: Ask HN: Do you have any evidence that agentic coding works?

#40

Post by jermaustin1 »

edude03 wrote: post #4

I have the same experience despite using claude every day. As an funny anecdote: Someone I know wrote the code and the unit tests for a new feature with an agent. The code was subtly wrong, fine, it happens, but worse the 30 or so tests they added added 10 minutes to the test run time and they all essentially amounted to `expect(true).to.be(true)` because the LLM had worked around the code not working in the tests

This happens with me every time I try to get claude to write tests. I've given up on it. Instead I will write the tests if I really care enough to have tests.
Post reply on HN