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

241–250 of 508 posts

Re: ChatGPT agent: bridging research and action

#241

Post by ipaddr »

bugbuddy wrote: post #160
ameliaquining wrote: post #157

Earlier quoted context omitted.

The Gartner hype cycle assumes a single fundamental technical breakthrough, and describes the process of the market figuring out what it is and isn't good for. This isn't straightforwardly applicable to LLMs because the question of what they're good for is a moving target; the foundation models are actually getting more capable every few months, which wasn't true of cryptocurrency or self-driving cars. At least some…

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.

It's saving healthcare costs for those who solved their problem and never go in which would not be reflected in service inflation costs.

Re: ChatGPT agent: bridging research and action

#242

Post by novaRom »

Today I made like a 100 of merge request reviews, manually inspecting all the diffs, and approving those I evaluated as valid needed contributions. I wonder if agents can help with similar workflows. It requires deep kind of knowledge of project's goals, ability to respect all the constraints and planning. But I'm certain it's doable.

Re: ChatGPT agent: bridging research and action

#243

Post by maxlin »

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…

The act of trying to make that 2% appear like "minimal, dismissable" is almost a mass psychosis in the AI world at times it seems like.

A few comparisons:

>Pressing the button: $1 >Knowing which button to press: $9,999 Those 2% copy-paste changes are the $9.999 and might take as long to find as rest of the work.

Also: SCE to AUX.

Re: ChatGPT agent: bridging research and action

#244

Post by hiq »

taf2 wrote: post #175
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 the question then is what's the human error rate... We know we're not perfect... So if you're 100% rested and only have to find the edge case bug, maybe you'll usually find it vs you're burned out getting it 98% of the way there and fail to see the 2% of the time bugs... Wording here is tricky to explain but I think what we'll find is this helps us get that much closer... Of course when you spend your time bu…

The problem with this spreadsheet task is that you don't know whether you got only 2% wrong (just rounded some numbers) or way more (e.g. did it get confused and mistook a 2023 PDF with one from 1993?), and checking things yourself is still quite tedious unless there's good support for this in the tool.

At least with humans you have things like reputation (has this person been reliable) or if you did things yourself, you have some good idea of how diligent you've been.

Re: ChatGPT agent: bridging research and action

#245

Post by crowcroft »

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…

Almost anyone can add something to people's calendars as well (of course people don't accept random invites but they can appear).

If this kind of agent becomes wide spread hackers would be silly not to send out phishing email invites that simply contain the prompts they want to inject.

Re: ChatGPT agent: bridging research and action

#246

Post by slg »

chatmasta wrote: post #233
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…

Yeah, people complaining about accuracy of AI-generated code should be examining their code review procedures. It shouldn’t matter if the code was generated by a senior employee, an intern, or an LLM wielded by either of them. If your review process isn’t catching mistakes, then the review process needs to be fixed. This is especially true in open source where contributions aren’t limited to employees who passed a hi…

This is taking what I said further than intended. I'm not saying the standard review process should catch the AI generated mistakes. I'm saying this work is at the level of someone who can and will make plenty of stupid mistakes. It therefore needs to be thoroughly reviewed by the person using before it is even up to the standard of a typical employee's work that the normal review process generally assumes.

Re: ChatGPT agent: bridging research and action

#247

Post by htrp »

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

Re: ChatGPT agent: bridging research and action

#248

Post by vidarh »

torginus wrote: post #111
samtp wrote: post #82

Earlier quoted context omitted.

This is the exact same issue that I've had trying to use LLMs for anything that needs to be precise such as multi-step data pipelines. The code it produces will look correct and produce a result that seems correct. But when you do quality checks on the end data, you'll notice that things are not adding up. So then you have to dig into all this overly verbose code to identify the 3-4 subtle flaws with how it transform…

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 entirely uncontroversial.

Even most maximalists would agree at least with the latter, and the former largely depends on definitions.

As someone who uses Claude extensively, I think of it almost as a slightly dumb alien intelligence - it can speak like a human adult, but makes mistakes a human adult generally wouldn't, and that combinstion breaks the heuristics we use to judge competency,and often lead people to overestimate these models.

Claude writes about half of my code now, so I'm overall bullish on LLMs, but it saves me less than half of my time.

The savings improve as I learn how to better judge what it is competent at, and where it merely sounds competent and needs serious guardrails and oversight, but there's certainly a long way to go before it'd make sense to argue they think like humans.

Re: ChatGPT agent: bridging research and action

#250

Post by prettyblocks »

imiric wrote: post #238
simantel wrote: post #197

Earlier quoted context omitted.

> It feels kind of odd that almost no one is talking about self-driving now, compared to how hot of a topic it used to be Probably because it's just here now? More people take Waymo than Lyft each day in SF.

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.
Post reply on HN