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

261–270 of 508 posts

Re: ChatGPT agent: bridging research and action

#261

Post by bugbuddy »

ameliaquining wrote: post #184
bugbuddy wrote: post #160

Earlier quoted context omitted.

Could you please expand on your point about expanding scopes? I am waiting earnestly for all the cheaper services that these expansions promise. You know cheaper white-collar-services like accounting, tax, and healthcare etc. The last reports saw accelerating service inflation. Someone is lying. Please tell me who.

Hence why I said potential applications. Each new generation of models is capable, according to evaluations, of doing things that previous models couldn't that prima facie have potential commercial applications (e.g., because they are similar to things that humans get paid to do today). Not all of them will necessarily work out commercially at that capability level; that's what the Gartner hype cycle is about. But be…

It sounds like people should just ignore those pesky ROI questions. In the long run, we are all dead so let’s just invest now and worry about the actual low level details of delivering on the economy-wide efficiency later.

As capital allocators, we can just keep threatening the worker class with replacing their jobs with LLMs to keep the wages low and have some fun playing monopoly in the meantime. Also, we get to hire these super smart AI researchers people (aka the smartest and most valuable minds in the world) and hold the greatest trophies. We win. End of story.

Re: ChatGPT agent: bridging research and action

#262

Post by imiric »

prettyblocks wrote: post #250
imiric wrote: post #238

Earlier quoted context omitted.

It's "here" if you live in a handful of cities around the world, and travel within specific areas in those cities. Getting this tech deployed globally will take another decade or two, optimistically speaking.

Given how well it seems to be going in those specific areas, it seems like it's more of a regulatory issue than a technological one.

Ah, those pesky regulations that try to prevent road accidents...

If it's not a technological limitation, why aren't we seeing self-driving cars in countries with lax regulations? Mexico, Brazil, India, etc.

Tesla launched FSD in Mexico earlier this year, but you would think companies would be jumping at the opportunity to launch in markets with less regulation.

So this is largely a technological limitation. They have less driving data to train on, and the tech doesn't handle scenarios outside of the training dataset well.

Re: ChatGPT agent: bridging research and action

#263

Post by anoojb »

Why does this feature not have a DevX?

It seems to me that the 2-20% of use cases where ChatGPT Agent isn't able to perform it might make sense to have a plug-in run that can either guide the agent through the complex workflow or perform a deterministic action (e.g. API call).

Re: ChatGPT agent: bridging research and action

#264

Post by thorum »

Forgeties79 wrote: post #207
thorum wrote: post #202

Earlier quoted context omitted.

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…

>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. I think their point is that 10%, 1%, whatever %, the type of problem is a huge headache. In something like a complicated spreadsheet it can quickly become hours of looking for needles in the haystack, a search that wouldn't be necessary if AI didn't get it a…

I understand the idea. My position is that this is a largely speculative claim from people who have not spent much time seriously applying agents for spreadsheet or video editing work (since those agents didn’t even exist until now).

“Getting something almost right, no matter how close, can often be worse than not doing it at all” - true with human employees and with low quality agents, but not necessarily true with expert humans using high quality agents. The cost to throw a job at an agent and see what happens is so small that in actual practice, the experience is very different and most people don’t realize this yet.

Re: ChatGPT agent: bridging research and action

#265

Post by plaguuuuuu »

vidarh wrote: post #248
torginus wrote: post #111

Earlier quoted context omitted.

I'll get into hot water with this, but I still think LLMs do not think like humans do - as in the code is not a result of a trying to recreate a correct thought process in a programming language, but some sort of statistically most likely string that matches the input requirements, I used to have a non-technical manager like this - he'd watch out for the words I (and other engineers) said and in what context, and wou…

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 amygdala by thinking thoughts that deal with the response (don't worry about the exam, you've studied for it already)

LLMs don't have anything like that. Part of why they aren't great at some aspects of human behaviour. E.g. coding, choosing an appropriate level of abstraction - no fear of things becoming unmaintainable. Their approach is weird when doing agentic coding because they don't feel the fear of having to start over.

Emotions are important.

Re: ChatGPT agent: bridging research and action

#266

Post by threecheese »

2oMg3YWV26eKIs wrote: post #167

The security risks with this sound scary. Let's say you give it access to your email and calendar. Now it knows all of your deepest secrets. The linked article acknowledges that prompt injection is a risk for the agent: > Prompt injections are attempts by third parties to manipulate its behavior through malicious instructions that ChatGPT agent may encounter on the web while completing a task. For example, a maliciou…

Many of us have been partitioning our “computing” life into public and private segments, for example for social media, job search, or blogging. Maybe it’s time for another segment somewhere in the middle?

Something like lower risk private data, which could contain things like redacted calendar entries, de-identified, anonymized, or obfuscated email, or even low-risk thoughts, journals, and research.

I am Worried; I barely use ChatGPT for anything that could come back to hurt me later, like medical or psychological questions. I hear that lots of folks are finding utility here but I’m reticent.

Re: ChatGPT agent: bridging research and action

#267

Post by threecheese »

htrp wrote: post #247
bredren wrote: post #236

This solves a big issue for existing CLI agents, which is session persistence for users working from their own machines. With claude code, you usually start it from your own local terminal. Then you have access to all the code bases and other context you need and can provide that to the AI. But when you shut your laptop, or have network availability changes the show stops. I've solved this somewhat on MacOS using the…

Run dev on an actual server somewhere that doesn't shut down

Any thoughts on using Mosh here,for client connection persistence? Could Claude Code (et al) be orchestrated via SSH?

Re: ChatGPT agent: bridging research and action

#268

Post by mountainriver »

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.

We have a similar tool that can get around any of this, we built a custom desktop that runs on residential proxies. You can also train the agents to get better at computer tasks https://www.agenttutor.com/

Re: ChatGPT agent: bridging research and action

#269

Post by gitgud »

achrono wrote: post #134
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.

In typical SV style, this is just to throw it out there and let second order effects build up. At some point I expect OpenAI to simply form a partnership with LinkedIn and Amazon. In fact, I suspect LinkedIn might even create a new tier that you'd have to use if you want to use LinkedIn via OpenAI.

Why would platforms like LinkedIn want this? Bots have never been good for social media…

Re: ChatGPT agent: bridging research and action

#270

Post by lossolo »

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 have a friend who's vibe-coding apps. He has a lot of them, like 15 or more, but most are only 60–90% complete (almost every feature is only 60-90% complete), which means almost nothing works properly. Last time he showed me something, it was sending the Supabase API key in the frontend with write permissions, so I could edit anything on his site just by inspecting the network tab in developer tools. The amount of technical debt and security issues building up over the coming years is going to be massive.
Post reply on HN