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

201–210 of 661 posts

Re: Zuckerberg says AI agent development going slower than expected

#201

Post by simonwthemonron »

simonw wrote: post #191
cyanydeez wrote: post #190

Earlier quoted context omitted.

the pessimistic take is their harness is no better than thise available and he thinks they all suck together. from a high level, these agents absolutely do not function as a rational human through even medium scoped problems. even when you try to add memory, you just multiply halucinated context which just makes it error out on tasks in harder to detect manner. hes likely trying to do mental gymnastics about the abso…

I expect it's a model problem and not a harness problem, purely because some of the best harnesses (including OpenAI Codex itself) are open source and can be very easily tried against a new model.

[dead]

Re: Zuckerberg says AI agent development going slower than expected

#202

Post by mikgp »

Jyaif wrote: post #165
mullingitover wrote: post #156

Having agents is like going from walking to having a bicycle. Business executives look at this and think "at this rate of progress we'll have self-driving cars in a few years!" and start making serious plans for that world. In reality I think we're going to be riding bikes for a long time. That situation of increased individual contributor productivity makes engineers more valuable , and increases the utility of engi…

Nobody knows if we are going to "just" be riding bikes for a long time. To give time for society to adapt I hope it's the case, but we really have no idea.

Right, but if your real assertion is “we have no idea”, it seems you should point your skepticism significantly more towards the people betting $100 billion dollars that self-driving cars are coming next year than the ones who aren’t.

Re: Zuckerberg says AI agent development going slower than expected

#203

Post by zamalek »

sdesol wrote: post #170
zamalek wrote: post #143

Earlier quoted context omitted.

> Can you just give an agent a desired outcome and let it work, unsupervised? Absolutely not. Ignoring instructions - whether in AGENTS.md or my prompt - is the worst of it, and it routinely happens. It just waives things that I explicitly told it to do as part of the design. Vibe coders (in the true sense, zero oversight) claim that you just need to prompt it carefully. That's completely untrue when faced with your…

> I even have "don't overrule me without asking" in my global AGENTS.md, and it simply doesn't do that. You really need to look into hooks based on your coding agent. This is very much a solved problem as I demonstrate with https://github.com/gitsense/pi-brains I have a test repo https://github.com/gitsense/gsc-rules-demos that shows how you can block and warn and do other things. You obviously can't have a "Don't ma…

So would that solve (most recent example):

The agreed architecture is to use signing between two micros, so that a third can orchestrate between them in zero trust way (and to prevent a distributed monolith). It just decides that we can trust the third and skips the signing.

Re: Zuckerberg says AI agent development going slower than expected

#204

Post by zamalek »

rogerrogerr wrote: post #157
zamalek wrote: post #143

Earlier quoted context omitted.

> Can you just give an agent a desired outcome and let it work, unsupervised? Absolutely not. Ignoring instructions - whether in AGENTS.md or my prompt - is the worst of it, and it routinely happens. It just waives things that I explicitly told it to do as part of the design. Vibe coders (in the true sense, zero oversight) claim that you just need to prompt it carefully. That's completely untrue when faced with your…

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.

Re: Zuckerberg says AI agent development going slower than expected

#205

Post by paytonjjones »

darth_avocado wrote: post #200
root_axis wrote: post #189

Earlier quoted context omitted.

The difference is a lot more than just throwing scale at it, pretty much everything useful comes from an evolving landscape of post-training techniques. Of course, param count and context length are also important because they increase the model's overall fidelity, but a base model without SFT, RHLF etc is effectively useless.

Correct. That is what I was trying to hint at. Yes, massive compute is needed to train ai, but it isn’t the only thing. A lot of research and experimentation goes into moving the marker just a little bit. Innovation can’t be forced into weekly sprints, it takes its own time.

Research and experimentation on neural nets has been going on since the 70s (arguably much earlier even), but the lions share of capability changes has all been in the last couple years.

Scale was really the unlock; the new pre and post training techniques and architectures are very cool and useful but they definitely aren't the differentiators when comparing to the previous era of NLP.

Re: Zuckerberg says AI agent development going slower than expected

#206

Post by zamalek »

lanstin wrote: post #161
zamalek wrote: post #143

Earlier quoted context omitted.

> Can you just give an agent a desired outcome and let it work, unsupervised? Absolutely not. Ignoring instructions - whether in AGENTS.md or my prompt - is the worst of it, and it routinely happens. It just waives things that I explicitly told it to do as part of the design. Vibe coders (in the true sense, zero oversight) claim that you just need to prompt it carefully. That's completely untrue when faced with your…

Your context isn’t to give it orders, they just don’t work like that. Your context (AGENTS.me, skills, per-request context we are sending in for each request to bots) is to give it the info it needs in the language category it’s trained for the answers you want; you have to give it a clear instruction each prompt. Basically, when you have a long session, you can see this by saying, ok, now moving onto another thing,…

> Basically, when you have a long session, you can see this by saying, ok, now moving onto another thing, blah blah blah

I try to avoid > 200k contexts, as the 1M context is where I first saw the massive decrease in reliability.

And my AGENTS is really short, and I said it was ignoring decisions in the prompt.

Re: Zuckerberg says AI agent development going slower than expected

#207

Post by HarHarVeryFunny »

You'd have thought that Zuck's previous failures to make the things he dreams about (e.g. Metaverse, decent in-house AI) materialize might have made him a bit more cautious about betting the farm on things that don't exist, especially when he's expecting someone else (the AI agent folks) to make it happen!

I suppose you have to admire the conviction: I'll fire my developers today because REAL SOON NOW I'll be able to replace them with AGI!

Re: Zuckerberg says AI agent development going slower than expected

#208

Post by zamalek »

ls612 wrote: post #182
zamalek wrote: post #143

Earlier quoted context omitted.

> Can you just give an agent a desired outcome and let it work, unsupervised? Absolutely not. Ignoring instructions - whether in AGENTS.md or my prompt - is the worst of it, and it routinely happens. It just waives things that I explicitly told it to do as part of the design. Vibe coders (in the true sense, zero oversight) claim that you just need to prompt it carefully. That's completely untrue when faced with your…

In my limited testing Fable is far better at obeying CLAUDE.MD than Opus is.

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.

Re: Zuckerberg says AI agent development going slower than expected

#209

Post by argee »

grey-area wrote: post #158
zamalek wrote: post #143

Earlier quoted context omitted.

> Can you just give an agent a desired outcome and let it work, unsupervised? Absolutely not. Ignoring instructions - whether in AGENTS.md or my prompt - is the worst of it, and it routinely happens. It just waives things that I explicitly told it to do as part of the design. Vibe coders (in the true sense, zero oversight) claim that you just need to prompt it carefully. That's completely untrue when faced with your…

These are word generators, not agents, I’m really not sure why people think they could be capable agents (ie independent) when they consistently ignore instructions, generate the wrong things and then double down when questioned, etc etc. You’ve been sold something that simply doesn’t work for the purported use case (intelligence) and instead is like a stupid database of all world knowledge with the appearance of int…

> instead is like a stupid database of all world knowledge with the appearance of intelligence.

A "stupid" database would be better, based on what I get when I ask whether all of Oregon state is North of New York City. Indian English has a word for it: oversmart.

Re: Zuckerberg says AI agent development going slower than expected

#210

Post by 1attice »

atomicnumber3 wrote: post #199
ffsm8 wrote: post #198

Earlier quoted context omitted.

Fwiw , you're conflating multiple things and consequently drawing premature conclusions. It can be massively over hyped for it's current capacity and decimate the white collar work. A lot of the difference of opinion is down to their point of view. At my dayjob, LLMs will not live up to anything because the enterprise is not structured to take advantage of it's strength. That's unlikely to change within the foreseeab…

Sure, naturally. And yet parent commenter is remarking that simultaneously no AI-true-believer startups have supplanted the old money, and simultaneously despite much talk the bigcos have not slashed headcount to tiny AI-powered teams.

Depends on the bigco IMO. I'm not sure what kind of layoff numbers for Year Three of genAI would grab your attention, but I assure you, hundreds of thousands have mine.
Post reply on HN