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

Zuckerberg says AI agent development going slower than expected

reuters.com

Post reply on HN
Print view View original

651–660 of 661 posts

Re: Zuckerberg says AI agent development going slower than expected

#651

Post by KronisLV »

zamalek wrote: post #204
rogerrogerr wrote: post #157

Earlier quoted context omitted.

I’m convinced the magic bullet is deterministic checks. Linters, static analyzers, etc. Whatever you can do to create deterministic gates that the LLM simply must overcome to reach a “done” state, do it. Has been making a huge difference for my team, but sister teams are so invested in writing the perfect Make No Mistakes prompt that they just can’t see it. Basically I treat it like a junior dev. We don’t get junior…

Wouldn't have helped, sibling comment: https://news.ycombinator.com/item?id=48797883 Architectural decisions are not lintable.

> Architectural decisions are not lintable.

I made a tool called ProjectLint to lint architectural decisions and anything that ESLint and ArchUnit and others like that wouldn't be a good fit for. It's not public yet, but is fairly rudimentary and based on Go + goja: https://github.com/dop251/goja

You write rules in ESLint, it makes sure that they're followed. If it's a file in your repo, it can obviously be checked. Now whether you can describe your architecture well enough to lint it (at least the stuff you care about enforcing), that's a different question.

In my case it's more like: "Oh, the AI messed up this pattern, but it will need to be followed N more times in the future, better write another projectlint rule." After a while, you can even copy them over between projects, as long as they're following the same conventions.

In the same spirit of https://www.archunit.org/

Re: Zuckerberg says AI agent development going slower than expected

#652

Post by KetoManx64 »

Laurel1234 wrote: post #646
KetoManx64 wrote: post #594

Earlier quoted context omitted.

As in the government takes it out of your paycheck automatically, and you'll go to prison if you refuse to pay it?

Yep, and that's literally the same exact mechanism we need the Epstein-class parasites to pay into as well.

Yeah, because the solution to all the corruption is just more taxes and giving politicians more power and money.

Re: Zuckerberg says AI agent development going slower than expected

#653

Post by tukantje »

DanielHB wrote: post #590
SkyBelow wrote: post #560

Earlier quoted context omitted.

>Many developers are too focused on delivery value compared to maintenance cost. The way this is worded feels like it leaves the blame on developers. Aren't these developers focused on exactly what they are being judged by? Shouldn't we say it is the management who is too focused on delivery value compared to maintenance cost? Is it the developer's job to guide management or the manager's job to request guidance, ass…

I don't think so, my experience is that most often falls into two scenarios: 1) The devs pushing for more complex solutions, covering obscure edge case scenarios, feature-creep, "future-architecturing" because they are more interesting to implement. Classic over-engineering problems. 2) The features the managers actually want are usually boring or annoying to implement and the devs just work around any big architectu…

How is covering obscure edge case scenarios overengineering?

Re: Zuckerberg says AI agent development going slower than expected

#654

Post by tangweigang »

efficax wrote: post #115

I was worried this time last year that by this time this year, companies would have slashed their engineering teams down to a handful and everything would be driven by mostly autonomous agents with human guidance. But it just hasn't happened. Do I write all my code with an agent now? Yes. Can you just give an agent a desired outcome and let it work, unsupervised? Absolutely not. I can produce more code than I used to…

[flagged]

Re: Zuckerberg says AI agent development going slower than expected

#655

Post by alt227 »

Kudos wrote: post #370
hatefulheart wrote: post #362

Earlier quoted context omitted.

I’m sorry, what’s the question? Genuinely not sure. I’ll rephrase, Zuckerberg would certainly enjoy agentic coding to be a wild success because it means less staff and more products he could fail to create.

Again, Zuck's success criteria don't necessarily align with that of others. In fact, I'd expect his success criteria are substantially different to most.

Making money? Seems to be the common success criteria for all.

Re: Zuckerberg says AI agent development going slower than expected

#656

Post by throw-qqqqq »

tmule wrote: post #497
throw-qqqqq wrote: post #491

Earlier quoted context omitted.

> He's not an AI scientist or an AI researcher Perhaps he employs some, you know, to inform him on the topic?

The same folks who informed him about how awesome Behemoth was?

Snide remarks, both of you :)

My point was not that Meta has the best AI researchers/engineers.

My point was it should not matter if Zuck is a PHP developer or whatever, instead of an AI researcher, as he employs a lot of people with those exact skills.

I made no comment about how Meta is doing in the AI race, so it’s a bit besides the point IMO, but you did make me smile :)

Re: Zuckerberg says AI agent development going slower than expected

#657

Post by reverius42 »

eiifr1 wrote: post #635
DanielHB wrote: post #458

Earlier quoted context omitted.

> Lines of code are a liability, not an asset. I have been saying this for years, I once had a heated argument about a small system of maybe 1000 lines of code that was technically superior and more scalable but was freaking 1000 lines of code to maintain compared to the quick and dirty 10 lines of code it was suppose to abstract and make generic (for future use of course). That with also countless debates over insig…

"Lines of code are a liability, not an asset." wrong framing imo EXCESS lines of code are a liability. Code of course is an asset.. what other real asset is producing cash-flows? lol come on.

It's apples and oranges. Lines of code is just a measurement. You can't look at a whole codebase and say "these X lines are essential, those Y lines are excess, delete those" -- the lines interact with each other to create the whole thing.

It would be like saying "Weight in kilograms of course is an asset for an airplane. That's what keeps it in the air. What other real asset is the airplane made of?"

Re: Zuckerberg says AI agent development going slower than expected

#658

Post by penpendian »

yepyoukno wrote: post #74
penpendian wrote: post #72

i bet he wants some calculative shit

Or some fuzzy yet inevitably reliable shit. The modern trend is to think intelligence is generative “like compression” or “predicting next in sequence” rather than iteratively reducing uncertainty, like those fault tolerant humans.

emergence is a good philosophical concept but really bad if done in engineering that is why i never develop llm but hardness or use llm at most

Re: Zuckerberg says AI agent development going slower than expected

#659

Post by shimman »

alyandon wrote: post #573
frenchtoast8 wrote: post #546

Earlier quoted context omitted.

Gabe Newell (president, not CEO) comes to mind

I really worry about what happens to Valve as a company after he steps down.

Hopefully they'd stop introducing gambling to children.
Post reply on HN