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

301–310 of 508 posts

Re: ChatGPT agent: bridging research and action

#301

Post by collingreen »

freeone3000 wrote: post #284
bo1024 wrote: post #271

Earlier quoted context omitted.

It sounds like you’re saying that good tests are enough to ensure good code even when programmers are unskilled and just rewrite until they pass the tests. I’m very skeptical.

It may not be a provable take, but it’s also not absurd. This is the concept behind modern TDD (as seen in frameworks like cucumber): Someone with product knowledge writes the tests in a DSL Someone skilled writes the verbs to make the DSL function correctly And from there, any amount of skill is irrelevant: either the tests pass, or they fail. One could hook up a markov chain to a javascript sourcebook and eventuall…

> One could hook up a markov chain to a javascript sourcebook and eventually get working code out.

Can they? Either the dsl is so detailed and specific as to be just code with extra steps or there is a lot of ground not covered by the test cases with landmines that a million monkeys with typewriters could unwittingly step on.

The bugs that exist while the tests pass are often the most brutal - first to find and understand and secondly when they occasionally reveal that a fundamental assumption was wrong.

Re: ChatGPT agent: bridging research and action

#302

Post by chaos_emergent »

lairv wrote: post #213
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…

In general most of the previous AI "breakthrough" in the last decade were backed by proper scientific research and ideas: - AlphaGo/AlphaZero (MCTS) - OpenAI Five (PPO) - GPT 1/2/3 (Transformers) - Dall-e 1/2, Stable Diffusion (CLIP, Diffusion) - ChatGPT (RLHF) - SORA (Diffusion Transformers) "Agents" is a marketing term and isn't backed by anything. There is little data available, so it's hard to have generally capa…

I disagree that there isn't an innovation.

The technology for reasoning models is the ability to do RL on verifiable tasks, with the some (as-of-yet unpublished, but well-known) search over reasoning chains, with a (presumably neural) reasoning fragment proposal machine, and a (presumably neural) scoring machine for those reasoning fragments.

The technology for agents is effectively the same, with some currently-in-R&D way to scale the training architecture for longer-horizon tasks. ChatGPT agent or o3/o4-mini are likely the first published models that take advantage of this research.

It's fairly obvious that this is the direction that all the AI labs are going if you go to SF house parties or listen to AI insiders like Dwarkesh Patel.

Re: ChatGPT agent: bridging research and action

#303

Post by tasty_freeze »

gitgud wrote: post #269
achrono wrote: post #134

Earlier quoted context omitted.

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…

If they are getting a cut of that premium subscription income, they'd want it if it nets them enough.

Re: ChatGPT agent: bridging research and action

#304

Post by Fraterkes »

ddp26 wrote: post #176

Predicted by the AI 2027 team in early April: > Mid 2025: Stumbling Agents The world sees its first glimpse of AI agents. Advertisements for computer-using agents emphasize the term “personal assistant”: you can prompt them with tasks like “order me a burrito on DoorDash” or “open my budget spreadsheet and sum this month’s expenses.” They will check in with you as needed: for example, to ask you to confirm purchases.…

The big crux of AI 2027 is the claims about exponential technological improvement. "Agents" are mostly a new frontend to the same technology openai has been selling for a while. Let's see if we're on track at the start of 2026

Re: ChatGPT agent: bridging research and action

#305

Post by lobochrome »

Aurornis wrote: post #127
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…

> 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 quip about 98% correct should be a red flag for anyone familiar with spreadsheets”

I disagree. Receiving a spreadsheet from a junior means I need to check it. If this gives me infinite additional juniors I’m good.

It’s this popular pattern of HN comments - expect AI to behave deterministically correct - while the whole world operates on stochastically correct all the time…

Re: ChatGPT agent: bridging research and action

#306

Post by guluarte »

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…

it now will take him 4-8hours plus a 200usd monthly bill, a win-win for everybody.

Re: ChatGPT agent: bridging research and action

#307

Post by FridgeSeal »

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…

It compounds too:

At a certain point, relentlessly checking for whether the model has got everything is more effort in turn than…doing it.

Moreover, is it actually a 4-8 hour job? Or is the person not using the right tool, is the better tool a sql query?

Half these “wow ai” examples feel like “oh my plates are dirty, better just buy more”.

Re: ChatGPT agent: bridging research and action

#308

Post by enneff »

lobochrome wrote: post #305
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 quip about 98% correct should be a red flag for anyone familiar with spreadsheets” I disagree. Receiving a spreadsheet from a junior means I need to check it. If this gives me infinite additional juniors I’m good. It’s this popular pattern of HN comments - expect AI to behave deterministically correct - while the whole world operates on stochastically correct all the time…

In my experience the value of junior contributors is that they will one day become senior contributors. Their work as juniors tends to require so much oversight and coaching from seniors that they are a net negative on forward progress in the short term, but the payoff is huge in the long term.

Re: ChatGPT agent: bridging research and action

#309

Post by guluarte »

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…

yep, the same problem with outsourcing, getting the 90% "done" is easy, the 10% is hard and completely depends on how the "90%" was archived

Re: ChatGPT agent: bridging research and action

#310

Post by dkga »

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…

Yes - and that is especially true for high-stakes processes in organizations. For example, accounting, HR benefits, taxation needs to be exactly right.
Post reply on HN