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

ChatGPT agent: bridging research and action

openai.com

Post reply on HN
Print view View original

391–400 of 508 posts

Re: ChatGPT agent: bridging research and action

#391

Post by vidarh »

ipaddr wrote: post #254
n2d4 wrote: post #148

Earlier quoted context omitted.

> said we'd have self driving cars "in a few years" back in 2015 And they wouldn't have been too far off! Waymo became L4 self-driving in 2021, and has been transporting people in the SF Bay Area without human supervision ever since. There are still barriers — cost, policies, trust — but the technology certainly is here.

Reminds me of electricity entering the market and the first DC power stations setup in New York to power a few buildings. It would have been impossible to replicate that model for everyone. AC solved the distance issue. That's where we are at with self driving. It can only operate in one small area, you can't own one. We're not even close to where we are with 3d printers today or the microwave in the 50s.

No, it can operate in several small areas, and the number of small areas it can operate in is a deployment issue. It certainly doesn't mean it is solved, but it is largely solved for a large proportion of rides, in as much as they can keep adding new small areas for a very long time without running out of growth-room even if the technology doesn't improve at all.

Re: ChatGPT agent: bridging research and action

#392

Post by vidarh »

plaguuuuuu wrote: post #265
vidarh wrote: post #248

Earlier quoted context omitted.

I think that if people say LLMs can never be made to think , that is bordering on a religious belief - it'd require humans to exceed the Turing computable (note also that saying they never can is very different from believing current architectures never will - it's entirely reasonable to believe it will take architectural advances to make it practically feasible). But saying they aren't thinking yet or like humans is…

Everyone has this impression that our internal monologue is what our brain is doing. It's not. We have all sorts of individual components that exist totally outside the realm of "token generation". E.g. the amygdala does its own thing in handling emotions/fear/survival, fires in response to anything that triggers emotion. We can modulate that with our conscious brain, but not directly - we have to basically hack the…

Unless we exceed the turing computable - which there isn't the tiniest shred of evidence for -, nothing we do is "outside the realm of 'token generation'". There is no reason why the token stream generated needs to be treated as equivalent to an internal monologue, or need to always be used to produce language at all, and Turing complete systems are computationally equivalent (they can all compute the same set of functions).

> Everyone has this impression that our internal monologue is what our brain is doing.

Not everyone has an internal monologue, so that would be utterly bizarre. Some people might believe this, but it is by no means relevant to Turing equivalence.

> Emotions are important.

Unless we exceed the Turing computable, our experience of emotions would be evidence that any Turing complete system can be made to act as if they experience emotions.

Re: ChatGPT agent: bridging research and action

#393

Post by vidarh »

mentalpiracy wrote: post #317
twalkz wrote: post #30

The "spreadsheet" example video is kind of funny: guy talks about how it normally takes him 4 to 8 hours to put together complicated, data-heavy reports. Now he fires off an agent request, goes to walk his dog, and comes back to a downloadable spreadsheet of dense data, which he pulls up and says "I think it got 98% of the information correct... I just needed to copy / paste a few things. If it can do 90 - 95% of the…

> "I think it got 98% of the information correct... I just needed to copy / paste a few things. If it can do 90 - 95% of the time consuming work, that will save you a ton of time" "Hello, yes, I would like to pollute my entire data store" is an insane a sales pitch. Start backing up your data lakes on physical media, there is going to be an outrageous market for low-background data in the future. semi-related: How ma…

How often will 98% correct data actually be worse? How often will it be better?

98% might well be disastrous, but I've seen enough awful quality human-produced data that without some benchmarks I'm not confident we know whether this would be better or worse.

Re: ChatGPT agent: bridging research and action

#394

Post by vidarh »

thorum wrote: post #202
twalkz wrote: post #30

The "spreadsheet" example video is kind of funny: guy talks about how it normally takes him 4 to 8 hours to put together complicated, data-heavy reports. Now he fires off an agent request, goes to walk his dog, and comes back to a downloadable spreadsheet of dense data, which he pulls up and says "I think it got 98% of the information correct... I just needed to copy / paste a few things. If it can do 90 - 95% of the…

People say this, but in my experience it’s not true. 1) The cognitive burden is much lower when the AI can correctly do 90% of the work. Yes, the remaining 10% still takes effort, but your mind has more space for it. 2) For experts who have a clear mental model of the task requirements, it’s generally less effort to fix an almost-correct solution than to invent the entire thing from scratch. The “starting cost” in me…

A lot of people here also make the assumption that the human user would make no errors.

What error rate this same person would find if reviewing spreadsheets made by other people seems like an inherently critical benchmark before we can even discuss whether this is a problem or an achievement.

Re: ChatGPT agent: bridging research and action

#395

Post by wltr »

intended wrote: post #367
slg wrote: post #225

Earlier quoted context omitted.

The proper use of these systems is to treat them like an intern or new grad hire. You can give them the work that none of the mid-tier or senior people want to do, thereby speeding up the team. But you will have to review their work thoroughly because there is a good chance they have no idea what they are actually doing. If you give them mission-critical work that demands accuracy or just let them have free rein with…

For this example - Let’s replace the word “intern” with “initial-stage-experts” or something. There’s a reason people invest their time with interns.

Yeah, most of us are mortal, that’s the reason.

Re: ChatGPT agent: bridging research and action

#396

Post by CaptainFever »

modeless wrote: post #139
pants2 wrote: post #70

I've been using OpenAI operator for some time - but more and more websites are blocking it, such as LinkedIn and Amazon. That's two key use-cases gone (applying to jobs and online shopping). Operator is pretty low-key, but once Agent starts getting popular, more sites will block it. They'll need to allow a proxy configuration or something like that.

Agents respecting robots.txt is clearly going to end soon. Users will be installing browser extensions or full browsers that run the actions on their local computer with the user's own cookie jar, IP address, etc.

I'm surprised older OpenAI agents respected robots.txt.

Expecting AI agents to respect robots.txt is like expecting browser extensions like uBlock Origins to respect "please-dont-adblock.txt".

Of course it's going to be ignored, because it's an unreasonable request, it's hard to detect, and the user agent works for the user, not the webmaster.

Assuming the agent is not requesting pages at an overly fast speed, of course. In that case, feel free to 429.

Q: but what about botnets-

I'm replying in the context of "Users will be installing browser extensions or full browsers that run the actions on their local computer with the user's own cookie jar, IP address, etc."

Re: ChatGPT agent: bridging research and action

#397

Post by psychoslave »

slg wrote: post #225
Aurornis wrote: post #127

Earlier quoted context omitted.

> how it normally takes him 4 to 8 hours to put together complicated, data-heavy reports. Now he fires off an agent request, goes to walk his dog, and comes back to a downloadable spreadsheet of dense data, which he pulls up and says "I think it got 98% of the information correct... This is where the AI hype bites people. A great use of AI in this situation would be to automate the collection and checking of data. Se…

The proper use of these systems is to treat them like an intern or new grad hire. You can give them the work that none of the mid-tier or senior people want to do, thereby speeding up the team. But you will have to review their work thoroughly because there is a good chance they have no idea what they are actually doing. If you give them mission-critical work that demands accuracy or just let them have free rein with…

What a awful way to think about internship.

The goal is to help people grow, so they can achieve things they would not have been able to deal with before gaining that additional experience. This might include boring dirty work, yes. But that means they thus prove they can overcome such a struggle, and so more experienced people should be expected to also be able to go though it - if there is no obvious more pleasant way to go.

What you say of interns regarding checks is just as true for any human out there, and the more power they are given, the more relevant it is to be vigilent, no matter their level of experience. Not only humans will make errors, but power games generally are very permeable to corruptible souls.

Re: ChatGPT agent: bridging research and action

#398

Post by Jommi »

buzzerbetrayed wrote: post #385
ghm2180 wrote: post #164

Earlier quoted context omitted.

You mean like calaude code's integration with play right ?

No, because playwright can be detected pretty easily and blocked. It needs to be (and will be) using the same browser that you regularly browse with.

detecting playwright is not "easy"... It can be done but its cat and mouse. Playwright in non headless mode is nearly impossible to detect.

Re: ChatGPT agent: bridging research and action

#399

Post by Culonavirus »

johnebgd wrote: post #388
OtherShrezzing wrote: post #281

Earlier quoted context omitted.

I’ve never experienced an intern who was remotely as mediocre and incapable of growth as an LLM.

I had an intern who didn’t shower. We had to have discussions about body odor in an office. AI/LLM’s are an improvement in that regard. They also do better work than that kid did. At least he had rich parents.

Wait, you had Asmongold work for you? Tell us more! xD

Re: ChatGPT agent: bridging research and action

#400

Post by posix86 »

AgentMatrixAI wrote: post #47

I'm not so optimistic as someone that works on agents for businesses and creating tools for it. The leap from low 90s to 99% is classic last mile problem for LLM agents. The more generic and spread an agent is (can-do-it-all) the more likely it will fail and disappoint. Can't help but feel many are optimizing happy paths in their demos and hiding the true reality. Doesn't mean there isn't a place for agents but rathe…

But that's how progress works! To me it makes sense that llms first manage to do 80% of the task, then 90, then 95, then 98, then 99, then 99.5, and so on. The last part IS the hardest, and each iteration of LLMs will get a bit further.

Just because it didn't reach 100% just yet doesn't mean that LLMs as a whole are doomed. In fact, the fact that they are slowly approaching 100% shows promise that there IS a future for LLMs, and that they still have the potential to change things fundamentally, more so than they did already.

Post reply on HN