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

71–80 of 389 posts

Re: The Eternal Sloptember

#71

Post by what »

simianwords wrote: post #32

People misunderstand how AI is used in coding in normal work environments. New feature requirement comes - maybe you need a new service or some new classes. You need to do some research first. You guide the AI with some prompts and give it some guidance on how to scenario-test it. It makes some classes, test methods. Maybe ~2000 lines and you do a quick verification, check if the overall idea looks okay. Ask it to fi…

Yes, just throw 2kloc over the wall for some feature. Your coworkers must love you.

Re: The Eternal Sloptember

#72

Post by simianwords »

vips7L wrote: post #62
simianwords wrote: post #32

People misunderstand how AI is used in coding in normal work environments. New feature requirement comes - maybe you need a new service or some new classes. You need to do some research first. You guide the AI with some prompts and give it some guidance on how to scenario-test it. It makes some classes, test methods. Maybe ~2000 lines and you do a quick verification, check if the overall idea looks okay. Ask it to fi…

If you don’t know what library to use in your specific language, do you think you know enough to have an LLM generate most of it?

YES. This line of thought is exactly why people are still skeptical of LLM's.

LLM's are directionally right and if their answer "fits" then I take it at face value.

I wrote a blog detailing the computational difference between "generation" and "verification" and why it matters for LLM's: https://simianwords.bearblog.dev/the-generation-vs-verificat...

As an example: I asked the LLM "synonym for "provides" that also means "places" on you" and it gave me 5 answers and I immediately knew the right one was "confers". How? It just fits. Just like most things.

Re: The Eternal Sloptember

#73

Post by nilirl »

bluegatty wrote: post #52
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.

At a granular level, it's almost guaranteed that you cannot write better code than an agent. Agents now are writing extremely consistent, normalized canonical code, that usually compiles the first time. Right out of the 'textbook'. For what it's trying to do - it writes nearly perfect code. The only thing you could nominally disagree with are some of the conventions and idioms. It 'writes a perfect novel, in perfect…

Syntax is the least of my concerns.

Modelling a problem is what I'm concerned about. And I'm currently better than any AI agent at doing that, given enough time.

Re: The Eternal Sloptember

#74

Post by cafkafk »

I think a lot of the problem with the current discourse is how black-and-white it is. Either you're a luddite or "ai pilled".

In most cases, LLMs can get you 80-95% of the way, sometimes less, sometimes more. And heck, sometimes, it just gets you somewhere wrong.

But it seems everyone is arguing about whether LLMs can be perfect software engineers in isolation running in a closet, and using that to say that LLMs do not have a massive potential in other scenarios.

Sometimes, I like to imagine how much more productive most organizations could be from the things that the internet gave us, even to this day. Most companies never really do even a fraction of what is possible. That helps to ground my view of LLMs as well.

The fault dear Brutus isn't in our language models, but in ourselves.

Re: The Eternal Sloptember

#75

Post by fontain »

andrewflnr wrote: post #31
fontain wrote: post #6

We all remember cryptocurrency. Everyone in tech proclaimed fiat was dead, every office buzzed with talk of every possible way that cryptocurrency could be used, billions of dollars flooded in to projects losing money hand over fist. The cynics reacted to the froth with outright rejection of the idea. And today… cryptocurrency exists, it has some use, but it didn’t take over the world, it didn’t kill fiat, it was use…

I wish people would stop comparing AI with cryptocurrency. The hype/perception was the only thing that was similar between them. The fundamental usefulness of the respective technologies are not comparable.

That's the fallacy. You think technology usefulness dictates the outcomes. There are billions of people living in poverty the world over, starving every day, we have the technology and resources to solve that right now, we have for decades, but we don't because we don't want to.

Could AI technology change the world? Sure. Will it? That depends on so much more than what the technology can do. Why are we all still working 40 hours a week? Why are people still hungry? We could have radically changed our world with the technology we have had for decades. Yet, we have not, we have continued, nothing has really changed.

The internet is a great example. What is the most impactful part of the internet today? Social media. Social media has radically changed our culture. What is social media? A database, a few endpoints and an app? The technology is the least consequential part, the consequence comes from how we use it.

Nerds focus on what is possible with the technology, not what society is likely to do with it. What evidence is there that AI is going to change the world? What change is going to come from... being able to generate plausible sounding text? From being able to instruct agents? How many companies are using garbage software from 20 years ago despite dozens of revolutionarily better equivalents being available out there today that could have drastically reshaped their workforce? What are agents if not better macros? How many businesses have hundreds of employees doing the same tasks over and over again that could have been replaced by a few macros? How much of the code that you and I have written in our careers has already been written before?

The fundamental usefulness is the least important part of a technology when discussing how that technology will impact the world.

Re: The Eternal Sloptember

#76

Post by imron »

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…

Here's one that hit the frontpage recently:

https://blog.k10s.dev/im-going-back-to-writing-code-by-hand/

Re: The Eternal Sloptember

#77

Post by latentsea »

jofzar wrote: post #57
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'd love to see examples of issues that are so big that they warrant reverting to manual coding Ah I see your org hasnt yet had an outage caused by a bad LLM code push.

This shouldn't actually change virtually anything. We had this happen recently, and were able to rollback within minutes. Devs hand-coding stuff breaks things too. If you already have good observability, fast rollback processes, and feature flag new changes plus do % based rollouts to limit the blast-radius, then it's more or less the same.

Re: The Eternal Sloptember

#78

Post by rakel_rakel »

> The bottom performers won’t have that self check. They are the ones producing 10x output with the agents. What do you think is happening to the average output of that organization?

Nailed it!

At my last place this was encouraged (by non-technical leadership driving the AI adoption policies, as well as setting salaries) and seen as a huge win.

The "step change in number of created PR's" was celebrated (cult-style), and by one of the (co) CEO's praised as a paradigm shift of the same magnitude as the personal computer. Meanwhile, I was stuck finding insta-reject level bugs in pull requests from people one-shotting 6000 line PR's "finally solving" long-standing issues from the backlog. Needless to say I left.

Re: The Eternal Sloptember

#79

Post by DeathArrow »

latentsea wrote: post #67
sodafountan wrote: post #49

Earlier quoted context omitted.

Yes, I don't have anything important to say other than I 100% agree with this comment. AI in its current state is akin to Stack Overflow and Google on steroids, but from my experience, it doesn't do well building out full-scale applications other than perhaps some initial scaffolding. If I were to use it against a legacy, rather poorly written codebase, where the code may be hard to understand without some in-depth a…

> Yes, I don't have anything important to say other than I 100% agree with this comment. AI in its current state is akin to Stack Overflow and Google on steroids, but from my experience, it doesn't do well building out full-scale applications other than perhaps some initial scaffolding. We're currently using it to build out a full-scale application. It does as well as you care to coax into doing tbh. You have to inve…

>It does as well as you care to coax into doing tbh. You have to invest heavily in harness engineering, and at least my experience has been that as you do that, the results improve.

That is also my experience.

When starting a project I observe how the agent fails, I add new rules to the harness to prevent it from falling and repeat the process until I am happy with the output.

Re: The Eternal Sloptember

#80

Post by jhanschoo »

I don't think Geohot has a good idea about LeCun and Hutter's views on the limitations of LLMs. I think that on abstract, textual domains, LLMs perform superbly, and they would agree. I am not too well-informed about LeCun and Hutter's views either, but I think that:

LeCun thinks that LLMs are a bad fit for AI that understands the physical, dynamical systems that we inhabit, and that understanding this is necessary for AGI/ASI.

I don't know that Hutter is bearish on LLMs, but Hutter is interested in AI that can reason exceptionally well given infinite compute, and approximations of such a reasoning AI. I think he is open to the idea that LLMs can be such an approximation.

Post reply on HN