ChatGPT agent: bridging research and action • Hacker News Board

Re: ChatGPT agent: bridging research and action

#431

Post by cheschire » Fri, Jul 18, 2025, 12:19 PM UTC

divan wrote: post #218

And I'm still waiting for the simple feature – the ability to edit documents in projects. I use projects for working on different documents - articles, research, scripts, etc. And would absolutely love to write it paragraph after paragraph with the help of ChatGPT for phrasing and using the project knowledge. Or using voice mode - i.e. on a walk "Hey, where did we finish that document - let's continue. Read the last…

Have you tried writing text in VS Code? I haven’t ever considered the use case before this moment and don’t have a system available to test.

But basically would it be successful if you had a workspace and used the coding agent to write text instead?

As a use case, consider the act of writing a novel where you might have a folder with files that each contain a skeleton of a chapter, then another folder with the first draft of each chapter in separate files, then another folder for the second draft, and so on.

Maybe not the best architecture but I just had the idea 20 seconds ago so it could use some cook time.

Re: ChatGPT agent: bridging research and action

#432

Post by cluckindan » Fri, Jul 18, 2025, 12:21 PM UTC

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.

I had a coworker who only showered once every few days after exercise, and never used soap or shampoo. He had no body odor, which could not be said about all employees, including management.

It’s that John Dewey quote from a parent post all over again.

Re: ChatGPT agent: bridging research and action

#433

Post by fkyoureadthedoc » Fri, Jul 18, 2025, 12:23 PM UTC

skeeter2020 wrote: post #257

fkyoureadthedoc wrote: post #174

Earlier quoted context omitted.

I don't know why everyone is so confident that jobs will be lost. When we invented power tools did we fire everyone that builds stuff, or did we just build more stuff?

if you replace "power tools" with industrial automation it's easy to cherry pick extremes from either side. Manufacturing? a lot of jobs displaced, maybe not lost.

That would be analogous to RPA maybe, and sure that has eliminated many roles. But software development and other similarly complex ever changing tasks have not been automated in the same way, and it's not even close to happening. Rote repetitive tasks with some decision making involved, probably on the chopping block.

Re: ChatGPT agent: bridging research and action

#434

Post by bredren » Fri, Jul 18, 2025, 12:38 PM UTC

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

> 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.

Re: ChatGPT agent: bridging research and action

#435

Post by paradite » Fri, Jul 18, 2025, 12:48 PM UTC

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…

Agents have been a field in AI long since 1990s.

MDP, Q learning, TD, RL, PPO are basically all about agent.

What we have today is still very much the same field as it was.

Re: ChatGPT agent: bridging research and action

#436

Post by mcntsh » Fri, Jul 18, 2025, 1:10 PM UTC

falcor84 wrote: post #179

tomashubelbauer wrote: post #168

Earlier quoted context omitted.

I wonder how many people will think they are being clever by using the Playwright MCP or browser extensions to bypass robots.txt on the sites blocking the direct use of ChatGPT Agent and will end up with their primary Google/LinkedIn/whatever accounts blocked for robotic activity.

I don't know how others are using it, but when I ask Claude to use playwright, it's for ad-hoc tasks which look nothing like old school scraping, and I don't see why it should bother anyone.

Claude doesn't look at advertisements.

Re: ChatGPT agent: bridging research and action

#437

Post by coderatlarge » Fri, Jul 18, 2025, 1:15 PM UTC

bluefirebrand wrote: post #320

Terretta wrote: post #285

Earlier quoted context omitted.

What about a coach's ability for improving instruction?

The point of coaching a Junior is so they improve their skills for next time What would be the point of coaching an LLM? You will just have to coach it again and again

coaching a junior doesn’t just improve the junior. It also tends to improve the senior.

Re: ChatGPT agent: bridging research and action

#438

Post by idiotsecant » Fri, Jul 18, 2025, 1:20 PM UTC

psychoslave wrote: post #397

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…

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…

The goal of internships in a for profit company is not the personal growth of the intern. This is a nice sentiment but the function of the company is to make money, so an intern with net negative productivity doesn't make sense when goals are quarterly financials.

Re: ChatGPT agent: bridging research and action

#439

Post by idiotsecant » Fri, Jul 18, 2025, 1:21 PM UTC

cluckindan wrote: post #432

johnebgd wrote: post #388

Earlier quoted context omitted.

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.

I had a coworker who only showered once every few days after exercise, and never used soap or shampoo. He had no body odor, which could not be said about all employees, including management. It’s that John Dewey quote from a parent post all over again.

Was he Asian? Seems like somehow asians win the genetic lottery in the stink generation department.

Re: ChatGPT agent: bridging research and action

#440

Post by chaos_emergent » Fri, Jul 18, 2025, 1:31 PM UTC

Fraterkes wrote: post #425

chaos_emergent wrote: post #421

Earlier quoted context omitted.

The same technology that checks notes has been in the wild for 7 months?

What is your point? We’re talking about the ai 2027 predictions here, which were made 4 months ago. 4 is “checks notes” less than 7

the point is that minimizing 4 months as an insufficient timeline along which to prove out ones ability to predict a sequence of events is dumb when the rate of progress is incredibly fast.