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

251–260 of 389 posts

Re: The Eternal Sloptember

#251

Post by Ekaros »

bruce511 wrote: post #197
soperj wrote: post #160

Earlier quoted context omitted.

It's funny, but the more I know about the true Luddites, the more I see their point of view. " the original Luddites were primarily protesting against machinery used to "fraudulently and deceitfully" manufacture inferior goods, bypass labor standards, and strip skilled artisans of their livelihoods."

Goods are usually (although not always) inferior when made by a machine. A hand-crafted solid wood table is still superior to something from Ikea. Of course hand made tables are expensive. They service a sliver of the market. Ikea serves the rest of us who'd prefer not to eat off the floor. Fundamentally, Luddites didn't like being replaced by a machine. They were skilled workers, who used to have very desirable skil…

I wonder what percentage of wooden furniture is truly hand-crafted in whole chain. That is felled with hand-made tools by hand. Transportation maybe can be ignored. Then hand sawed without power tools. All other tools after that being hand made from ground up. Like saws, planes, sand paper, glues(most likely at least some parts are glued together wood)... Most likely vanishingly small number.

Re: The Eternal Sloptember

#252

Post by chrisco255 »

DeathArrow wrote: post #61

To me this sounds like an old cobbler complaining that machines aren't producing good shoes if left unsupervised and that the old process of making shoes completely by hand is far superior. So what he is telling us? That agents are not infaillable and they are not capable to one shot complex software and they do not produce perfect code? We know what and the solution is to use agents for what they are good at and wor…

Modern shoes are made by a mix of machine and hand. There is still quite a bit of manual labor to produce shoes: https://www.youtube.com/watch?v=bK8pcAYapXQ

This is effectively what's happening to software. We are getting some forms of automation but I believe there's plenty of manual work and coordination left for humans to do.

Re: The Eternal Sloptember

#253

Post by zer0tonin »

Xenoamorphous wrote: post #179
maxnevermind wrote: post #93

Earlier quoted context omitted.

What type of projects you work on, in particular how rich it is in novelty, non-googlable data points and non-trivial project-specific deviations from industry standards?

Even if agents failed at that I'd wager that's a very small percentage of software projects anyway.

It's basically every game targetting consoles. Good luck finding any real infos about the Nintendo SDK API on Google.

Re: The Eternal Sloptember

#254

Post by farhanhubble »

wiseowise wrote: post #211
farhanhubble wrote: post #176

Earlier quoted context omitted.

That's fair. In all honesty I'm already feeling challenged but given how much time I save I can set aside some time to keep myself sharp. I can learn more languages. Additionally, as pointed out by others, I'm trading coding effort for design and and strategy, which generally control business outcomes a lot more. Having said that, I won't use AI for production system if I don't understand the programming constructs i…

> In all honesty I'm already feeling challenged but given how much time I save And how much is that?

Easily 99 percent on most tasks. As an example, for a Python project with a dozen modules and ~50 files,a simple instruction like "Design a config file backed by Pydantic to store the project's settings. Keep the models modular" sets up nested Pydantic models, moves the settings to sensibly named JSON fields and updates the code to use Pydantic classes everywhere. Takes a few minutes maybe. Manually done the same task would take me half a few hours in the best case and a day in the worst case.

Re: The Eternal Sloptember

#255

Post by Alex_L_Wood »

cheevly wrote: post #144
Alex_L_Wood wrote: post #91

Earlier quoted context omitted.

It's not just that, but the core is just that, even with reasoning models. Harness can only get you closer to the good result, but can't save you from every pitfall. As for PM analogy - don't forget that models don't learn and keep doing same stupid stuff they were doing a month ago.

Agents are perfectly capable of learning. Why would the model need to learn? The harness and tooling are all that matter.

They aren't, it's just populating context window until "memory" is pushed out.

Re: The Eternal Sloptember

#256

Post by chrisco255 »

simianwords wrote: post #237
kelnos wrote: post #103

Earlier quoted context omitted.

The author is not arguing against your bet. I think the author wouldn't be surprised if you won that bet. But that doesn't change the argument he does make.

What is a bet that most charitably represents what the author would make? If there’s no such bet then it’s just whining. If there is then I’d like to know.

The author, George Hotz, owns an AI company: https://comma.ai/

He is just making a moment-in-time assessment of how he feels about current state of LLM coding. I don't think it's a super-strongly held opinion, I'm sure he would be willing to change his opinion if the next two years of LLM development produce exponentially better results.

Re: The Eternal Sloptember

#257

Post by jvidalv »

athrowaway3z wrote: post #152

This post hits the nail at a bit of an angle. The AI agents are great, and any expert can prompt them correctly to get good code. LLMs occasionally pick wrong patterns and start digging a hole, but this is why an expert is required. The code itself is just not worth writing when a detailed prompt can get you the same code typing 20x less text. Where I agree with the post is: The adoption of AI agents into software en…

Thanks for the message, is exactly what I have in my brain and how I'm seeing it unfold.

I'm lucky to be part of different codebases, +200 engineers codebase in a 10 years old company and code, +5 engineers on fresh code. My personal projects, that are beyond POC's, real users, hundreds of commits.

The LLM agent sweet spot is the last one, they are perfect, as I can contain most of the knowledge in my brain of how it works in/out. Speed is insane as a solo developer.

Then the 5 engineers codebase, is also really good, but here you already start to see the problems, thanks to agents you don't even need to care how it works, I have been working on it for +6 months, it uses TRPC and I don't even know (I don't care) how TRPC works. You feel that no one in the team really knows how stuff works at 100% (fresh codebase, we have build this ourselves!!).

Then there is the old codebase with +200 engineers, this is the worst of all of them, you described it perfectly, a bottomless pit of tech debt. This codebase before agents was an old non-typescript one, it was not perfect, but you could build a mental model and understand it perfectly after a few weeks working on it. Now, is a hot-mess of code duplication and the quality is degrading faster and faster as the code gets worse and the Claude Code adoption increases within the engineering team.

Not sure what will be the outcome of all this, but I wouldn't be surprised if some company wakes up in 2027 with a codebase that maintenance and development has increased by x100 fold thanks to Agents.

Re: The Eternal Sloptember

#258

Post by edg5000 »

fluxusars wrote: post #225

I think the ai-as-an-exoskeleton analogy is quite apt: 1. It still requires your intent to move in the right direction rather than being fully autonomous, and 2. It's too big and bulky to use for delicate tasks.

Yes. I think of it as a car or tractor (which is also a kind of exoskeleton). You still need intricate knowledge; it's really an amplifier. Steer it wrong and you'll have a 1000 (very hard to detect upfront) bugs in the blink of an eye. Indeed it's hard to wield. At a minimum you need to understand your harness at the character level - the exact shape of the context should be roughly known when operating a harness.

I'm very interested in APIs that allow client-side context construction rather than relying on opaque APIs concatenating strings from your JSON messages and injecting tool prompts. I found that generally, you can craft the entire context as a unicode string and just stuff it in the system message. This works best with models where the chat template is published.

Re: The Eternal Sloptember

#259

Post by ares623 »

swiftcoder wrote: post #161
tonyedgecombe wrote: post #110

Earlier quoted context omitted.

>I think a lot of the problem with the current discourse is how black-and-white it is. There is too much money involved for any rational debate.

> There is too much money involved for any rational debate. For the Sam Altmans of this world, sure, but how much money is the average AI booster commenting on HN actually standing to make?

I get an extra slice of pizza on fridays for being a good little engineer

Re: The Eternal Sloptember

#260

Post by edg5000 »

petterroea wrote: post #60

I think geohot is somewhat of a clown but I think he is speaking reason here and I'm happy to see voices address this. Most seniors I work with agree.

He did admit that he writes his posts in a slightly baity manner. They are his views, but he likes to make waves for the sake of it. It's a smart tactic; it helps his companies if he stays well-known. It's also just fun to read his inflammatory musings. I'm sure he emjoys writing them to.
Post reply on HN