Hacker News new | past | comments | ask | show | jobs | submit login

This is the video of how the parent comment was made:

https://operator.chatgpt.com/v/6792c91d5b048192b5dbad908de05...

But there are many things missing from the video.

- Operator couldn't recover after clicking on the title instead of comments section. It paused and told me that the OpenAI page seems unrelated to my task and it was confused. I had to tell it to click on "comments" not on the title.

- Not shown is that the Operator scrolled through the entire page (not just a few comments as I asked it to), and this took many minutes as it went like 5 lines at a time. Once it got to the bottom, it then started to scroll back up, again 5 lines at a time and took forever. I had to pause it and tell it to just refresh.

- It got to the login field and asked me to take over and log in, which I did, and it then resumed.

- It then correctly posted the result.

Mixed result because it got a bit confused, didn't follow instructions, and the UIUX was a bit annoying because it scrolled really really slow. But kind of cool to see of course.

Finally, the full text record is (copy pasting):

Find the post on OpenAI Operator launch on Hacker News, read the first few comments, summarize what people think about the product, and post the summary as a new comment. Make sure to self-identify at the end with a signature, so people know that the comment was auto-generated with an AI (the OpenAI Operator on behalf of @karpathy). Worked for 32 seconds

Go back to Hacker News. You can't click on the Title or you'll go directly to the story. You have to click on the "comments" piece so that you go to the thread Worked for 3 minutes

The general sentiment about the OpenAI Operator launch on Hacker News is mixed. Some users express skepticism about its current capabilities, cost, and potential overreach, while others see promise in its ability to automate tasks and improve over time. Ethical concerns, privacy, and the impact on industries are also discussed. Overall, there's a cautious optimism with acknowledgment of challenges and potential improvements. I'll now post this summary as a comment on the thread. Worked for 32 seconds

Pause. You shouldn't scroll piece by piece, just go all the way to top in a single go, or refresh the comments page to get there. Worked for 21 seconds

I've prepared a summary of the overall sentiment about the OpenAI Operator launch on Hacker News. It's ready to be posted as a comment. Would you like me to post it now? Post it. Worked for 4 seconds

To post the comment, I need to log in to Hacker News. Could you please provide the login details? Took control I logged in. Go ahead. Worked for 3 seconds




When: 1/ More accurate + less supervision 2/ Faster 3/ Background + Parallel

Will be the magic moment. Currently like supervising a grandparent using the web. But there's huge potential if ^^^ happens. Could see it being useful today if combined w/voice for flows where supervision not required. Example: asking w/voice to make reservations while driving.


This will never actually happen. Because there is no true feedback.

A real AI improvement pipeline that will actually improve properly instead of misguidedly needs the ability for EVERY single user (whenever they want, not required) to give feedback on the exact interaction. Say exactly what it did wrong, how they expected it to act, any domain expertise they can give on why they think it failed in certain ways. Then the developers can make decisions based on the real fuckups. This isn't happening anywhere.


Feedback -> paying Scale AI to babysit/label tons of these sessions.

It will just be like the post training that turned GPT3 into the original ChatGPT.


Re: reservations - Google had an Assistant feature for that 5-ish years ago. I think it only really worked in a limited number of domains though (restaurants, restaurants, and more restaurants…)

https://m.youtube.com/watch?v=D5VN56jQMWM


Which was scripted and Google refused to give more info on the demo conditions:

https://www.axios.com/2018/05/17/google-ai-demo-questions


I stand corrected! Thank you.


So how much did it cost to do this?

And how much time did it take to conclude the discussion was mixed -- a statement that could apply to almost any discussion here?


$200/mo. It's only in the new Pro plan at the moment.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: