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

641–650 of 661 posts

Re: Zuckerberg says AI agent development going slower than expected

#641

Post by kingds »

ben_w wrote: post #434
andrewaylett wrote: post #424

Earlier quoted context omitted.

The thing is: I could produce 2-3 times as much code as before _without_ an LLM, if I didn't care about my colleagues' ability to review my output properly. Lines of code are a liability, not an asset. You want as few of them as you can get away with, without compromising the actual asset: the functionality. A huge part of the job of Software Engineering is producing the right amount of code at the right time.

> Lines of code are a liability, not an asset. You want as few of them as you can get away with, without compromising the actual asset: the functionality. > A huge part of the job of Software Engineering is producing the right amount of code at the right time. Absolutely true, however my experience says that the correlation between "good software engineering practices" and "positive business outcomes" is, at best, sm…

I'd argue PayPal was a successful business, not a successful piece of software.

Re: Zuckerberg says AI agent development going slower than expected

#642

Post by zamalek »

Atotalnoob wrote: post #640
zamalek wrote: post #208

Earlier quoted context omitted.

From what I can tell, the "established wisdom" is to get Fable to plan and Opus to implement (for cost purposes). The problem there is that Opus could ignore whatever it likes from Fable's plan.

Doesn’t that kill your token caching changing models midstream?

The Claude harness effectively summarizes the discovery into a plan document, clears, and starts with just that summary - so you'd be clearing context regardless.

Re: Zuckerberg says AI agent development going slower than expected

#643

Post by pipes »

efficax wrote: post #629
pipes wrote: post #614

Earlier quoted context omitted.

I'm really struggling to get an agent to write code I'm happy with. It's mostly pretty awful. I've a fairly simple c# coding style. But simple is proving a bit more difficult to convey than I thought. I get it to produce code. I then have to spend along time convincing myself it's correct. If I don't I end up embarrassing myself when a coworker reviews it, questions it and it's obvious I don't properly understand it.…

work from tests to implementation. Validate the tests, and work with the agent to ensure there are not more cases that need testing. Then you can let the agent implement the code and you can refine it until it's simple enough but covers the test cases. TDD is the only way to use agents effectively, imo

Thanks. I have been doing this tdd abd it's a big improvement but the code is still pretty awful. Two skills I rely on are Matt pococks grill-me and his tdd. These massively helped, and technically the code generated is correct but it's still hard to follow and bloated.

https://github.com/mattpocock/skills/blob/main/skills/produc...

Re: Zuckerberg says AI agent development going slower than expected

#644

Post by ben_w »

kingds wrote: post #641
ben_w wrote: post #434

Earlier quoted context omitted.

> Lines of code are a liability, not an asset. You want as few of them as you can get away with, without compromising the actual asset: the functionality. > A huge part of the job of Software Engineering is producing the right amount of code at the right time. Absolutely true, however my experience says that the correlation between "good software engineering practices" and "positive business outcomes" is, at best, sm…

I'd argue PayPal was a successful business, not a successful piece of software.

That's kind of the point.

The software only had to be good enough to support the business. It doesn't have to win a Turing Award, and probably wouldn't help the business if it did.

Re: Zuckerberg says AI agent development going slower than expected

#645

Post by p_kuni »

cube00 wrote: post #591
p_kuni wrote: post #483

Earlier quoted context omitted.

Why does your harness allow the LLM to generate output that can disable rules & checks?

I have no idea because Google Antigravity is closed source.

Although I don't use it, Antigravity should be configurable to prevent reads / writes to certain files. You should definitely do that and ideally configure a hook to automatically run the linter after the LLM completes, then feed it back to the LLM if it's red. Don't prompt your agent to do stuff, build your loop in a deterministic manner.

Re: Zuckerberg says AI agent development going slower than expected

#646

Post by Laurel1234 »

KetoManx64 wrote: post #594
Laurel1234 wrote: post #395

Earlier quoted context omitted.

> How much of your money do you spend on paying for kids school lunches, paying medical bills of terminally ill kids and paying off the student loans of graduates? A third of my salary each month.

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.

Re: Zuckerberg says AI agent development going slower than expected

#647

Post by rldjbpin »

it is amazing that meta continues to burn money and keep afloat. ads DO really make money, especially when they are going to overtake google in this [1].

to all the critics, i would suggest letting him/them cook. the snowden-era privacy concerns was exactly around ai getting trained or using personal data, and they have a treasure trove of it.

their money dump do sometimes also spend money on r&d unrelated to the current mindhive topics. we never know what the scatterbrain approach may give birth to tomorrow.

do be critical and vocal on how they squeeze money out of other areas or how they increase their revenue by ruining our lives instead.

[1] https://news.ycombinator.com/item?id=47758569

Re: Zuckerberg says AI agent development going slower than expected

#650

Post by evilduck »

throwaway27448 wrote: post #541
cafebabbe wrote: post #520

Earlier quoted context omitted.

Honest question, is there a single successful large investment made by Meta recently ? I just know about the abject failures :)

llama has been generally useful.

llama was unintentionally released and has been a flash in the pan for them since. They've failed to capitalize on it at all post-v2. v3 models were a launch mess and quickly surpassed. The only thing it has left in 2026 is name recognition. Honestly their non-LLM things are more important and relevant, like their SAM models. https://ai.meta.com/resources/models-and-libraries/ but none of these seem to be making them serious money or exist and standalone products.
Post reply on HN