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

Andrej Karpathy: Software in the era of AI [video]

youtube.com

Post reply on HN
Print view View original

181–190 of 827 posts

Re: Andrej Karpathy: Software in the era of AI [video]

#181

Post by tlb »

OvbiousError wrote: post #160
abdullin wrote: post #102

Tight feedback loops are the key in working productively with software. I see that in codebases up to 700k lines of code (legacy 30yo 4GL ERP systems). The best part is that AI-driven systems are fine with running even more tight loops than what a sane human would tolerate. Eg. running full linting, testing and E2E/simulation suite after any minor change. Or generating 4 versions of PR for the same task so that the h…

I don't think the human is the problem here, but the time it takes to run the full testing suite.

Yes, and (some near-future) AI is also more patient and better at multitasking than a reasonable human. It can make a change, submit for full fuzzing, and if there's a problem it can continue with the saved context it had when making the change. It can work on 100s of such changes in parallel, while a human trying to do this would mix up the reasons for the change with all the other changes they'd done by the time the fuzzing result came back.

LLMs are worse at many things than human programmers, so you have to try to compensate by leveraging the things they're better at. Don't give up with "they're bad at such and such" until you've tried using their strengths.

Re: Andrej Karpathy: Software in the era of AI [video]

#182

Post by TeMPOraL »

khalic wrote: post #177

His dismissal of smaller and local models suggests he underestimates their improvement potential. Give phi4 a run and see what I mean.

He ain't dismissing them. Comparing local/"open" model to Linux (and closed services to Windows and MacOS) is high praise. It's also accurate.

Re: Andrej Karpathy: Software in the era of AI [video]

#184

Post by PeterStuer »

nilirl wrote: post #54

Where do these analogies break down? 1. Similar cost structure to electricity, but non-essential utility (currently)? 2. Like an operating system, but with non-determinism? 3. Like programming, but ...? Where does the programming analogy break down?

Define non-essenti

The way I see dependency in office ("knowledge") work:

- pre-(computing) history. We are at the office, we work

- dawn of the pc: my computer is down, work halts

- dawn of the lan: the network is down, work halts

- dawn of the Internet: the Internet connection is down, work halts (- dawn of the LLM: ChatGPT is down, work halts (<- for many, we are here already)

Re: Andrej Karpathy: Software in the era of AI [video]

#185

Post by sriram_malhar »

khalic wrote: post #177

His dismissal of smaller and local models suggests he underestimates their improvement potential. Give phi4 a run and see what I mean.

Of all the things you could suggest, a lack of understanding is not one that can be pinned on Karpathy. He does know his technical stuff.

Re: Andrej Karpathy: Software in the era of AI [video]

#186

Post by impossiblefork »

ActorNightly wrote: post #43
anythingworks wrote: post #5

loved the analogies! Karpathy is consistently one of the clearest thinkers out there. interesting that Waymo could do uninterrupted trips back in 2013, wonder what took them so long to expand? regulation? tailend of driving optimization issues? noticed one of the slides had a cross over 'AGI 2027'... ai-2027.com :)

> Karpathy is consistently one of the clearest thinkers out there. Eh, he ran Teslas self driving division and put them into a direction that is never going to fully work. What they should have done is a) trained a neural net to represent sequence of frames into a physical environment, and b)leveraged Mu Zero, so that self driving system basically builds out parallel simulations into the future, and does a search on…

I don't think that would have worked either.

But if they'd gone for radars and lidars and a bunch of sensors and then enough processing hardware to actually fuse that, then I think they could have built something that had a chance of working.

Re: Andrej Karpathy: Software in the era of AI [video]

#187

Post by sensanaty »

mentalgear wrote: post #157

Meanwhile, I asked this morning Claude 4 to write a simple EXIF normalizer. After two rounds of prompting it to double-check its code, I still had to point out that it makes no sense to load the entire image for re-orientating if the EXIF orientation is fine in the first place. Vibe vs reality, and anyone actually working in the space daily can attest how brittle these systems are. Maybe this changes in SWE with more…

There's also those instances where Microsoft unleashed Copilot on the .NET repo, and it resulted in the most hilariously terrible PRs that required the maintainers to basically tell Copilot every single step it should take to fix the issue. They were basically writing the PRs themselves at that point, except doing it through an intermediary that was much dumber, slower and less practical than them.

And don't get me started on my own experiences with these things, and no, I'm not a luddite, I've tried my damndest and have followed all the cutting-edge advice you see posted on HN and elsewhere.

Time and time again, the reality of these tools falls flat on their face while people like Andrej hype things up as if we're 5 minutes away from having Claude become Skynet or whatever, or as he puts it, before we enter the world of "Software 3.0" (coincidentally totally unrelated to Web 3.0 and the grift we had to endure there, I'm sure).

To intercept the common arguments,

- no I'm not saying LLMs are useless or have no usecases

- yes there's a possibility if you extrapolate by current trends (https://xkcd.com/605/) that they indeed will be Skynet

- yes I've tried the latest and greatest model released 7 minutes ago to the best of my ability

- yes I've tried giving it prompts so detailed a literal infant could follow along and accomplish the task

- yes I've fiddled with providing it more/less context

- yes I've tried keeping it to a single chat rather than multiple chats, as well as vice versa

- yes I've tried Claude Code, Gemini Pro 2.5 With Deep Research, Roocode, Cursor, Junie, etc.

- yes I've tried having 50 different "agents" running and only choosing the best output form the lot.

I'm sure there's a new gotcha being written up as we speak, probably something along the lines of "Well for me it doubled my productivity!" and that's great, I'm genuinely happy for you if that's the case, but for me and my team who have been trying diligently to use these tools for anything that wasn't a microscopic toy project, it has fallen apart time and time again.

The idea of an application UI or god forbid an entire fucking Operating System being run via these bullshit generators is just laughable to me, it's like I'm living on a different planet.

Re: Andrej Karpathy: Software in the era of AI [video]

#188

Post by Zanfa »

shakna wrote: post #143
melvinmelih wrote: post #104

Earlier quoted context omitted.

> Driving is not a general problem, though. But what's driving a car? A generalist human brain that has been trained for ~30 hours to drive a car.

Human brain's aren't generalist! We have multiple parts of the brain that interact in vastly different ways! Your cerebellum won't be running the role of the pons. Most parts of the brain cannot take over for others. Self-healing is the exception, not the rule. Yes, we have a degree of neuroplasticity, but there are many limits. (Sidenote: Driver's license here is 240 hours.)

> Human brain's aren't generalist!

What? Human intelligence is literally how AGI is defined. Brain’s physical configuration is irrelevant.

Re: Andrej Karpathy: Software in the era of AI [video]

#189

Post by diggan »

kubb wrote: post #174
ramon156 wrote: post #172

Earlier quoted context omitted.

The real question is how long it'll take until they're not brittle

Or will they ever be reliable. Your question is already making an assumption.

They're reliable already if you change the way you approach them. These probabilistic token generators probably never will be "reliable" if you expect them to 100% always output exactly what you had in mind, without iterating in user-space (the prompts).

Re: Andrej Karpathy: Software in the era of AI [video]

#190

Post by diggan »

bgwalter wrote: post #183

I'd like to hear from Linux kernel developers. There is no significant software that has been written (plagiarized) by "AI". Why not ask the actual experts who deliver instead of talk? This whole thing is a religion.

What counts as "significant software"? Only kernels I guess?
Post reply on HN