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

231–240 of 508 posts

Re: ChatGPT agent: bridging research and action

#231

Post by closewith »

throw-qqqqq wrote: post #215
closewith wrote: post #171

Earlier quoted context omitted.

> There are in fact lots of tasks people complete immediately at 99.99% success rate at first iteration or 99.999% after self and peer checking work This is so absurd that I wonder if you're telling? Humans don't even have a 99.99% success rate in breathing, let alone any cognitive tasks.

> Humans don't even have a 99.99% success rate in breathing Will you please elaborate a little on this?

Humans cough or otherwise have to clear their airways about 1 in every 1,000 breaths, which is a 99.9% success rate.

Re: ChatGPT agent: bridging research and action

#232

Post by apwell23 »

gorbypark wrote: post #195
apwell23 wrote: post #62

Earlier quoted context omitted.

> It's great to see at least one company creating real AI agents. I am already doing the type of examples in that post with claude code. claude code is not just for code. this week i've been doing market research in real estate with claude code.

I opened up the app bundle of CC on macOS and CC is incredibly simple at its core! There’s about 14 tools (read, write, grep, bash, etc). The power is in the combination of the model, the tools and the system prompt/tool description prompts. It’s kind of mind blowing how well my cobbled together home brew version actually works. It doesn’t have the fancy CLI GUI but it is more or less performant as CC when running it…

> It’s kind of mind blowing how well my cobbled together home brew version actually works. It doesn’t have the fancy CLI GUI but it is more or less performant as CC when running it through the Sonnet API.

I've been thinking of rolling up my own too. but i don't want to use sonnet api since that is pay per use. I currently use cc with a pro plan that puts me in timeout after a quota is met and resets the quota in 4 hrs. that gives me a lot of peace of mind and is much cheaper.

Re: ChatGPT agent: bridging research and action

#233

Post by chatmasta »

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…

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 hiring screen.

Re: ChatGPT agent: bridging research and action

#234

Post by MattSayar »

samtp wrote: post #82
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…

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 just wrote a post on my site where the LLM had trouble with 1) clicking a button, 2) taking a screenshot, 3) repeat. The non-deterministic nature of LLMs is both a feature and a bug. That said, read/correct can sometimes be a preferable workflow to create/debug, especially if you don't know where to start with creating.

Re: ChatGPT agent: bridging research and action

#235

Post by seydor »

testfrequency wrote: post #219
seydor wrote: post #198

Earlier quoted context omitted.

Apple products are leading edge. Imagine if they waited until Samsung makes the perfect phone , then copy it. We re talking about european tech businesses being left behind, locked in a basement.

So you have a positive opinion when Apple does things after others, but Europe having a slower, cautious approach is treated as negative for you? What is your preference for Europe, complete floodgates open and never ending lawsuits over IP theft like we have in the USA currently over AI? The US is not the example of what’s working, it’s merely a demonstration of what is possible when you have limited, provoked regul…

I said apple does not do that. Apple invented the smartphone before samsung or anyone.

There is no such thing as "slow" in business. If you re slow you go out of business, you re no longer a business.

There is only one AI race. There is no second round. If you stay out of the race, you will be forever indebted to the AI winner, in the same way that we are entirely dependent on US internet technology currently (and this very forum)

Re: ChatGPT agent: bridging research and action

#236

Post by bredren »

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 app Amphetamine which allows the machine to go about its business with the laptop fully closed. But there are a variety of problems with this, including heat and wasted battery when put away for travel.

Another option is to just spin up a cloud instance and pull the same repos to there and run claude from there. Then connect via tmux and let loose.

But there are (perhaps easy to overcome) ux issues with getting context up to that you just don't have if it is running locally.

The sandboxing maybe offers some sense of security--again something that can be possibly be handled by executing claude with a specially permissioned user role--which someone with John's use case in the video might want.

---

I think its interesting to see OpenAI trying to crack the Agent UX, possibly for a user type (non developer) that would appreciate its capabilities just as much but not need the ability to install any python package on the fly.

Re: ChatGPT agent: bridging research and action

#238

Post by imiric »

simantel wrote: post #197
ricardobayes wrote: post #76

Earlier quoted context omitted.

Of course, Pareto principle is at work here. In an adjacent field, self-driving, they are working on the last "20%" for almost a decade now. 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, with a lot of deep, moral, almost philosophical discussions.

> 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.

Re: ChatGPT agent: bridging research and action

#239

Post by htrp »

thornewolf wrote: post #223
biker142541 wrote: post #204

Earlier quoted context omitted.

I just want to know what the insurance looks like behind this, lol. An agent mistakenly places an order for 500k instead of 500 stickers at some premium pricing tier above intended one. Sorry, read the fine print, and you're using at your own risk?

I haven't looked at OpenAI's ToS but try and track down a phrase called "indemnity clause". It's in some of Google's GCP ToS. TLDR it means "we (Google) will pay for ur lawsuit if something you do using our APIs get you sued" Not legal advice, etc.

>OpenAI’s indemnification obligations to API customers under the Agreement include any third party claim that Customer’s use or distribution of Output infringes a third party’s intellectual property right. This indemnity does not apply where: (i) Customer or Customer’s End Users knew or should have known the Output was infringing or likely to infringe, (ii) Customer or Customer’s End Users disabled, ignored, or did not use any relevant citation, filtering or safety features or restrictions provided by OpenAI, (iii) Output was modified, transformed, or used in combination with products or services not provided by or on behalf of OpenAI, (iv) Customer or its End Users did not have the right to use the Input or fine-tuning files to generate the allegedly infringing Output, (v) the claim alleges violation of trademark or related rights based on Customer’s or its End Users’ use of Output in trade or commerce, and (vi) the allegedly infringing Output is from content from a Third Party Offering.

Bullet 1 on service terms https://openai.com/policies/service-terms/

Re: ChatGPT agent: bridging research and action

#240

Post by amccollum »

n2d4 wrote: post #148
dingnuts wrote: post #106

Earlier quoted context omitted.

The critics of the current AI buzz certainly have been drawing comparisons to self driving cars as LLMs inch along with their logarithmic curve of improvement that's been clear since the GPT-2 days. Whenever someone tells me how these models are going to make white collar professions obsolete in five years, I remind them that the people making these predictions 1) said we'd have self driving cars "in a few years" bac…

> 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.

People were saying we would all be getting in our cars and taking a nap on our morning commute. We are clearly still a pretty long ways off from self-driving being as ubiquitous as it was claimed it would be.
Post reply on HN