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

The Eternal Sloptember

geohot.github.io

Post reply on HN
Print view View original

331–340 of 389 posts

Re: The Eternal Sloptember

#331

Post by swordsith »

swiftcoder wrote: post #163
Nition wrote: post #17

With the level of ability that AI is at right now, I've found it useful personally to think of it something like a very good search over existing knowledge. Another step up in searchability in the lineage of reference books, stack overflow, GitHub etc. Programmers are rewriting and reinventing the same techniques more often than any other vocation I can think of, and so we were primed for a really good search over pr…

> Programmers are rewriting and reinventing the same techniques more often than any other vocation I can think of And the answer to that is clearly a tool that makes rewriting/reinventing cheaper than actually packaging nice reusable libraries

Nice reusable libraries are still a core part of most AI projects, but honestly I think it's not a terrible approach with all the updating dependency malware issues with stuff like NPM.

Re: The Eternal Sloptember

#332

Post by swordsith »

4ndrewl wrote: post #128
farhanhubble wrote: post #14

I'm in the "haven't written any code in a while" boat ATM. I'd love to see examples of issues that are so big that they warrant reverting to manual coding. My main issue has been the inconsistent quality across between model releases and the tendency to insert older APIs or documentation, especially with command line tools. I can understand if the model struggles with a million line monolithic codebase with a decade…

> I'm in the "haven't written any code in a while" boat ATM How long do you think it will be before you can't write any code because you're out of practice? One of the dangers of engineering management is that it can turn you into a person that can no longer do the thing. Does that even matter?

How long will it be until you can't spin the thread and fabricate your clothes stitch by stitch because you're out of practice?

Re: The Eternal Sloptember

#333

Post by bluegatty »

esikich wrote: post #129
bluegatty wrote: post #106

Earlier quoted context omitted.

Yes, exactly, it's 'us' not the AI, which is great. Why on earth would we ever remotely compare a 'tool' to 'a software engineer' ? The 'great delusion' is not that 'AI can't code' - because obviously it can, and very well. The problem is the 'anthropomorphism' and all this AGI nonsense. If we called it 'Stochastic Mechanisms' and did not 'personalize' our prompts, refer to them as 'chat' or give them 'personalities'…

You are a tool. You're a human resource, from the perspective of the organization. That pushes buttons on bunch of other tools. That's why you compare it. Edit: I don't mean tool as a perjoritive.

There are innumerable other software and process technologies that we use - and never before have we compared them to 'Engineers'.

The 'tool of the system' analogy is not an unreasonable point of discussion but it does not help us in this scenario.

Re: The Eternal Sloptember

#334

Post by parineum »

Supermancho wrote: post #322
parineum wrote: post #132

Earlier quoted context omitted.

> the quality of the output is the quality of your guidance I wish you just started with the copout.

How is it a copout? These exercises are making an assumption that developers have been given even more context.

It's the LLM version of "You're holding it wrong."

Re: The Eternal Sloptember

#335

Post by peteforde »

sevenseacat wrote: post #307
tardedmeme wrote: post #169

Earlier quoted context omitted.

antirez is famous for creating Redis, which took a dump in quality and everyone switched to a fork called Valkey.

and Steve Yegge is currently just burning mountains of money with Gas Town or whatever came after that

While I don't actually disagree - to me, Gas Town sounds literally insane - I suspect that if you reframe his work to compare it against the cost of developing a new medication or chip fabrication technique, you can make a strong argument that he's putting his money where his mouth is to see how far he can take a new technology. He's doing science! And I think that's admirable, even if nothing comes of it.

When I think of how much money gets wasted on gambling apps and how much human potential gets wasted watching reality television and compare that to Steve going full Alexander Shulgin with LLMs, the comparison really falls flat.

Re: The Eternal Sloptember

#336

Post by swiftcoder »

swordsith wrote: post #331
swiftcoder wrote: post #163

Earlier quoted context omitted.

> Programmers are rewriting and reinventing the same techniques more often than any other vocation I can think of And the answer to that is clearly a tool that makes rewriting/reinventing cheaper than actually packaging nice reusable libraries

Nice reusable libraries are still a core part of most AI projects, but honestly I think it's not a terrible approach with all the updating dependency malware issues with stuff like NPM.

> I think it's not a terrible approach with all the updating dependency malware issues with stuff like NPM

I think in this instance, the only thing worse than a zero day in your dependency tree, is a zero day you don't know your LLM vendored directly into your codebase...

Re: The Eternal Sloptember

#337

Post by intended »

bandrami wrote: post #13
intended wrote: post #7

If nothing else, Eternal Sloptember is a term that seems obvious once you have it. I can’t believe this is the first time I’m seeing it.

If you were on Usenet before '93 the words still haunt you

I phrased it poorly, I haven’t heard the term sloptember.

Eternal September is the kind of trivia that let me know if someone is a grey beard or not.

Re: The Eternal Sloptember

#338

Post by phatfish »

nilirl wrote: post #38

I agree that I can write better code than an agent. But it can write working code much faster than I can. And in a lot of cases, unfortunately, faster beats better.

I suspect is very hard to get a consultant that doesn't hand over a repo of AI generated nonsense right now. For the reason above, they are (usually) under time pressure to deliver, and they can wash their hands of the results at the end of the contract.

I am at 2 for 2 at the moment in the "infrastructure as code" arena (I wasn't involved with choosing to use a consultant, just dealing with the output). Which is an area that AI was supposed to eat for lunch. And it seems like it should, DSLs with a narrower scope seem perfect for an LLM, but I'm not convinced.

I think the issue is, infrastructure DSLs like Terraform or Azure Bicep are distilling down an architecture that has complex interactions and often needs a lot of "inside baseball" knowledge from outside of the code to create a congruent result. Unless you feed a bible of markdown files to the LLM to guide it in the right direction the output goes off the rails fast. The time spend creating the bible might as well be spent creating the code.

Of course there are areas where an LLM will definitely help, like re-factoring, stamping out boiler-plate or even building on a solid base. But attempt to create even a semi-complex architecture from scratch using a few paragraphs of prompt and you are asking for trouble.

The trouble with the consultants I have interacted with is they don't write the bible first, as far as i can tell they just iterate on slop and you end up with multiple 800+ line PowerShell scripts in IaC pipelines and other craziness that is almost impossible to unpick after they have gone.

Re: The Eternal Sloptember

#339

Post by wyager »

georgehotz wrote: post #92
wyager wrote: post #5

> They are a highly sophisticated statistical model designed to mimic the distribution of programming Are we really still doing this?

Author here. I have never said that phrase before this blog post and certainly understand the absurdity of it. I certainly don't mean that you need something biological or whatever consciousness might or might not be. However there's still a distinction. Unless I'm responding to an LLM, you had a childhood. You learned about the world and space and agency before you ever learned how to program. And you didn't learn i…

This description falls apart for two reasons

1. It only accurately describes pre-training 2. It ignores the existence of generalization

Next token prediction is just a training task, not "what the model does internally" in any meaningful sense

Re: The Eternal Sloptember

#340

Post by Supermancho »

parineum wrote: post #334
Supermancho wrote: post #322

Earlier quoted context omitted.

How is it a copout? These exercises are making an assumption that developers have been given even more context.

It's the LLM version of "You're holding it wrong."

I don't see how you think that's a cop out. Instructions are never laid out perfectly:

https://www.commitstrip.com/en/2016/08/25/a-very-comprehensi...

Holding LLMs to the standards of human contextual understanding without communicating sufficient context can be dispensed with, as fantasy.

Using LLMs you quickly learn how much can be inferred from existing, which is dynamic and particular to each model today. There will always be a gap in how much instruction is needed due to mismatches of existing versus intent. Current state, you don't need much to get a lot out that can be verified prior to merge.

Post reply on HN