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

A year of vibes

lucumr.pocoo.org

Post reply on HN
Print view View original

111–120 of 128 posts

Re: A year of vibes

#111

Post by simonw »

_alaya wrote: post #110
simonw wrote: post #4

I really feel this bit: > With agentic coding, part of what makes the models work today is knowing the mistakes. If you steer it back to an earlier state, you want the tool to remember what went wrong. There is, for lack of a better word, value in failures. As humans we might also benefit from knowing the paths that did not lead us anywhere, but for machines this is critical information. You notice this when you are…

Simon, I keep hoping that you will do one of your excellent reviews on Amp. It feels like the one 'major' agentic coding tool that is still flying under the radar. I intend to explore it myself of course but curious your take.

Amp, Cursor and OpenCode are the three that I'm most behind on I think. So many tools, so little time!

Re: A year of vibes

#112

Post by rootnod3 »

comex wrote: post #48
rootnod3 wrote: post #24

"I have seen some people be quite successful with this." Wait until those people hit a snafu and have to debug something in prod after they mindlessly handed their brains and critical thinking to a water-wasting behemoth and atrophied their minds. EDIT: typo, and yes I see the irony :D

Just be glad that there remains a concrete benefit to not atrophying your mind and deeply understanding your code. For now. In the long run, I suspect the behemoth will become just as capable at debugging and dealing with complexity as humans. At that point, human involvement in the actual code will be pointless, and the only remaining human skill needed will be properly directing the agents – the skill those people…

The only future I see is that prompts will become so refined that you give them all the requirements an they write the code for ya. And that prompt language has to be unambiguous and so detailed that you loop around and re-invented a programming language, just this time it wastes tons of water.

Re: A year of vibes

#113

Post by rootnod3 »

theshrike79 wrote: post #105
rootnod3 wrote: post #23

Sorry, but why would including the prompt in the pull request make any difference? Explain what you DID in the pull request. If you can't summarize it yourself, it means you didn't review it yourself, so why should I have to do it for you?

You're making assumptions, of course you add BOTH. The point of adding the "prompt", or the discussion with the LLM is learning. You can go back and see what was the exact conversation.

Sounds more like just adding a ton of wasted time for the reviewer to read through those discussions. At least summarize it yourself, e.g. "After discovering manpage XYZ, it became clear that the correct usage of this function is fooBar()".

Re: A year of vibes

#114

Post by neutronicus »

karthink wrote: post #54
neutronicus wrote: post #27

Earlier quoted context omitted.

Emacs gptel just produces md or org files. Of course the agentic capabilities are very much on a roll-your-own-in-elisp basis.

> agentic capabilities are very much on a roll-your-own-in-elisp basis I use gptel-agent[1] when I want agentic capabilities. It includes tools and supports sub-agents, but I haven't added support for Claude skills folders yet. Rolling back the chat is trivial (just move up or modify the chat buffer), rolling back changes to files needs some work. [1] https://github.com/karthink/gptel-agent

Oh, sick. Wasn't aware.

Don't think it's in Spacemacs yet but I'll have to try it out.

Re: A year of vibes

#115

Post by shimman »

pigpop wrote: post #109
shimman wrote: post #108

Earlier quoted context omitted.

I don't think using an AI company that relies on selling AI solutions to make money as a unbiased source of info, but what do I know? I'm not a VC investor and skeptical of the rich + elites in general. Usually the best rule of thumb is to be against anything these people are for.

Do you want me to link you directly to the repos and threads on that page, I can if you can't find them.

No, I'm good. I do find it telling they don't list one of the more public LLM adoptions being forced fed to MSFT workers:

https://github.com/dotnet/runtime/pull/115762

Re: A year of vibes

#116

Post by bigfishrunning »

> My biggest unexpected finding: we’re hitting limits of traditional tools for sharing code. The pull request model on GitHub doesn’t carry enough information to review AI generated code properly — I wish I could see the prompts that led to changes. It’s not just GitHub, it’s also git that is lacking.

I find when submitting a complex PR, i tend to do a self review, adding another layer of comments above those that are included in the code. Seems like a nice place to stuff prompts

Re: A year of vibes

#117

Post by tylervigen »

kashyapc wrote: post #17

"Because LLMs now not only help me program, I'm starting to rethink my relationship to those machines. I increasingly find it harder not to create parasocial bonds with some of the tools I use. I find this odd and discomforting [...] I have tried to train myself for two years, to think of these models as mere token tumblers, but that reductive view does not work for me any longer. " It's wild to read this bit. Of cou…

Ever since this post from two weeks ago [0], my wife and I have been referring to any LLM as “bag of words.” So you don’t say “Gemini said” or “I asked ChatGPT,” you say “the bag of words told me…”

I’ve found it very grounding, despite heavily using the bags of words.

[0] https://www.experimental-history.com/p/bag-of-words-have-mer...

Re: A year of vibes

#118

Post by ojr »

teaearlgraycold wrote: post #81
ojr wrote: post #42

In the next year developers need to realize normal people do not care about the tech stack or the tools used, there are far too many written thoughts and opinions and not enough polished deployed projects. From an industry standpoint it’s business as usual, acquihires from products that LLMs apparently couldn’t save.

They care - but only for how the tech stack affects the product quality. Show someone a bloated React site on 3G and compare their experience to an SSR competitor.

99% of the US population have access to 4G, caring about 3G is a wasted effort. The point I’m trying to make about tech stack is users don’t care if you used Gemini, ChatGPT or Claude to generate code.

As someone who hasn’t converted to SSR yet. My main reason why I am switching is SEO, the performance increase is a plus though.

Re: A year of vibes

#119

Post by theshrike79 »

rootnod3 wrote: post #113
theshrike79 wrote: post #105

Earlier quoted context omitted.

You're making assumptions, of course you add BOTH. The point of adding the "prompt", or the discussion with the LLM is learning. You can go back and see what was the exact conversation.

Sounds more like just adding a ton of wasted time for the reviewer to read through those discussions. At least summarize it yourself, e.g. "After discovering manpage XYZ, it became clear that the correct usage of this function is fooBar()".

Why would the reviewer need to read through discussions? The description + code should be just fine.

It's like having someone watch a livestream screen recording of you writing the code.

It's nice to have there IF you need to go back and learn something, but hardly a review requirement.

Post reply on HN