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

The port I couldn't ship

ammil.industries

Post reply on HN
Print view View original

21–30 of 101 posts

Re: The port I couldn't ship

#21

Post by johnfn »

jeffrallen wrote: post #12
esafak wrote: post #5

You don't know what the model is capable of until you try. Maybe today's models are not good enough. Try again next year.

This is true, but also: everything I try works! I simply cannot come up with tasks the LLMs can't do, when running in agent mode, with a feedback loop available to them. Giving a clear goal, and giving the agent a way to measure it's progress towards that goal is incredibly powerful. With the problem in the original article, I might have asked it to generate 100 test cases, and run them with the original Perl. Then I…

Really, you haven't found a single task they can't do? I like agents, but this seems a little unrealistic? Recently, I asked Codex and Claude both to "give me a single command to capture a performance profile while running a playwright test". Codex worked on this one for at least 2 hours and never succeeded, even though it really isn't that hard.

Re: The port I couldn't ship

#23

Post by simonw »

yeasku wrote: post #19
GaryBluto wrote: post #18

Earlier quoted context omitted.

> I think you halucinated this up. (Quote from original comment, pre malicious-edit) No point in responding to a troll, but for the other people who may be reading this comment chain, he's used LLMs for various tasks. Not to mention that he founded TextSynth, an entire service that revolves around them. https://textsynth.com/ https://bellard.org/ts_sms/

[flagged]

You're confused. The compression algorithm was something different. TextSynth is an LLM inference server, similar to (but older than) llama.cpp.

Re: The port I couldn't ship

#24

Post by dwaltrip »

yeasku wrote: post #19
GaryBluto wrote: post #18

Earlier quoted context omitted.

> I think you halucinated this up. (Quote from original comment, pre malicious-edit) No point in responding to a troll, but for the other people who may be reading this comment chain, he's used LLMs for various tasks. Not to mention that he founded TextSynth, an entire service that revolves around them. https://textsynth.com/ https://bellard.org/ts_sms/

[flagged]

> TextSynth provides access to large language, text-to-image, text-to-speech or speech-to-text models such as Mistral, Llama, Stable Diffusion, Whisper thru a REST API and a playground. They can be used for example for text completion, question answering, classification, chat, translation, image generation, speech generation, speech to text transcription, ...

???

Re: The port I couldn't ship

#25

Post by embedding-shape »

As always, the answer is "divide & conquer". Works for humans, works for LLMs. Divide the task into as small, easy to verify steps as possible, ideally steps you can automatically verify by running one command. Once done, either do it yourself or offload to LLM, if the design and task splitting is done properly, it shouldn't really matter. Task too difficult? Divide into smaller steps.

Re: The port I couldn't ship

#26

Post by embedding-shape »

tonnydourado wrote: post #15

I won't deny OP learned something in this process, but I can't help but wonder: if they spent the same time and effort just porting the code themselves, how much more would they have learned? Specially considering that the output would be essentially the same: a bunch of code that doesn't work.

I guess it depends on well people want to know things like "Perl (and C) library to web" skills. Personally, there are languages I don't want to learn, but for one reason or another, I have to change some details in a project that happen to use that language. Sure, I could sit down and learn enough of the language so I can do the thing, but if I don't like or want to use that language, the knowledge will eventually atrophy anyways, so why bother?

Re: The port I couldn't ship

#27

Post by itsangaris »

dwaltrip wrote: post #22

How many hours until someone else is able to get it to work? I consider myself a bit of an expert vibe engineer and the challenge is alluring :D

> A reader (or dare I say a wiser version of me), armed with a future model and dedicated to the task, will succeed with this port where I failed and that makes me uneasy.

Re: The port I couldn't ship

#28

Post by samdjstephens »

gortok wrote: post #3

While there's not a lot of meat on the bone for this post, one section of it reflects the overall problem with the idea of Claude-as-everything: > I spent weeks casually trying to replicate what took years to build. My inability to assess the complexity of the source material was matched by the inability of the models to understand what it was generating. When the trough of disillusionment hits, I anticipate this wil…

If LLMs stopped improving today I’m sure you would be correct- as it is I think it’s very hard to predict what the future holds and where the advancements take us.

I don’t see a particularly good reason why LLMs wouldn’t be able to do most programming tasks, with the limitation being our ability to specify the problem sufficiently well.

Re: The port I couldn't ship

#29

Post by yeasku »

simonw wrote: post #23
yeasku wrote: post #19

Earlier quoted context omitted.

[flagged]

You're confused. The compression algorithm was something different. TextSynth is an LLM inference server, similar to (but older than) llama.cpp.

Creating a llama.cpp like software is not using LLMs to develop software neither.

Re: The port I couldn't ship

#30

Post by aretu7888 »

dwaltrip wrote: post #22

How many hours until someone else is able to get it to work? I consider myself a bit of an expert vibe engineer and the challenge is alluring :D

You just need to know what you are doing. In this case, the problem is not "rewriting the logic" but "mapping Perl syntax to Typescript syntax" and "mapping Perl libs to Typescript libs". In other words, you'd be better off with an old-fashioned script that merely works on syntax mangling along with careful selection of dependencies (and maybe some manual labor around fixing the APIs of the consumers).

This is easy work, made hard by the "allure" of LLMs, which go from emphatic to emetic in the blink of an eye.

If you don't know what you are doing, you should stay away from LLMs if there is anything at all at stake.

Post reply on HN