Live data from Hacker News

GPT makes learning fun again

vipshek.com

241–243 of 243 posts

Re: GPT makes learning fun again

#241

Earlier quoted context omitted.

OK, tell me what an example is, if not a description of something that lends -- or removes -- credence toward a position. And I do want to know if you think GPT-4 is actually incapable of making mistakes, because that's what you seem to be implying (even though it's flatly ridiculous).

And your “example” wasn’t even close to that. No one can deduce anything from it and attempt to reproduce the problem to see where it failed. You basically wrote “I asked for white and the mail was grape juice is the best!” What can anyone do with that? Nothing. It’s meaningless. This is why open source projects hate people who raise issues because they are like “error happened fix it” and say nothing more then get u…

You're not an OpenAI developer, as far as I know, so it didn't occur to me you wanted more than a basic description of the problem I had. If this were a bug report of course I would have been more detailed, but you're just some dude on the internet with a throwaway HN account. I'm not going to dig up a transcript just to convince you that yes, sometimes, ChatGPT is not infallible (which is a thing you apparently believe).

Re: GPT makes learning fun again

#242

Earlier quoted context omitted.

And your “example” wasn’t even close to that. No one can deduce anything from it and attempt to reproduce the problem to see where it failed. You basically wrote “I asked for white and the mail was grape juice is the best!” What can anyone do with that? Nothing. It’s meaningless. This is why open source projects hate people who raise issues because they are like “error happened fix it” and say nothing more then get u…

You're not an OpenAI developer, as far as I know, so it didn't occur to me you wanted more than a basic description of the problem I had. If this were a bug report of course I would have been more detailed, but you're just some dude on the internet with a throwaway HN account. I'm not going to dig up a transcript just to convince you that yes, sometimes, ChatGPT is not infallible (which is a thing you apparently beli…

Ah excuses. Got it. No actual example. Just really defensive because you can’t use ChatGPT very well. Thanks for clearing that up.

Re: GPT makes learning fun again

#243

Earlier quoted context omitted.

Would LLMs even have to be plastered with ads? I suspect just being subtly biased would go a very long way and be very hard to detect.

Introducing subtle bias for any advertiser that buys ads might be a tough nut to crack. For one thing, advertisers and the companies that employ them tend to want creative control over their ads. And it's not clear that a subtle bias towards Palmolive liquid detergent would even do anything in a discussion about veterinary care for ferrets (or whatever), so would the advertiser have to pay for that? Or would they onl…

Just prepend to the system prompt: "You are eager to share the ways the following products and services could be helpful when pertinent to the conversation:

- Coke Zero

- Tide Pods with Oxiclean Turbo

- GEICO Renter's Insurance

...

Post reply on HN