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

31–40 of 508 posts

Re: ChatGPT agent: bridging research and action

#32

Post by Duanemclemore »

jjcm wrote: post #2

For me the most interesting example on this page is the sticker gif halfway down the page. Up until now, chatbots haven't really affected the real world for me†. This feels like one of the first moments where LLMs will start affecting the physical world. I type a prompt and something shows up at my doorstep. I wonder how much of the world economy will be driven by LLM-based orders in the next 10 years. † yes I'm awar…

It went viral more than a year ago, so maybe you've seen it. On the Ritual Industries instagram, Brian (the guy behind RI) posted a video where he gives voice instruction to his phone assistant, which put the text through chatgpt, which generated openscad code, which was fed to his bambu 3d printer, which successfully printed the object. Voice to Stuff.

I don't have ig anymore so I can't post the link, but it's easy to find if you do.

Re: ChatGPT agent: bridging research and action

#38

Post by rvz »

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 feels like either finding that 2% that's off (or dealing with 2% error) will be the time consuming part in a lot of cases.

The last '2%' (and in some benchmarks 20%) could cost as much as $100B+ more to make it perfect consistently without error.

This requirement does not apply to generating art. But for agentic tasks, errors at worst being 20% or at best being 2% for an agent may be unacceptable for mistakes.

As you said, if the agent makes an error in either of the steps in an agentic flow or task, the entire result would be incorrect and you would need to check over the entire work again to spot it.

Most will just throw it away and start over; wasting more tokens, money and time.

And no, it is not "AGI" either.

Re: ChatGPT agent: bridging research and action

#39

Post by pyman »

It's great to see at least one company creating real AI agents. The last six months have been agonising, reading article after article about people and companies claiming they've built and deployed AI agents, when in reality, they were just using OpenAI's API with a cron job or an event-driven system to orchestrate their GenAI scripts.
Post reply on HN