Live data from Hacker News

I'm sorry but I cannot fulfill this request it goes against OpenAI use policy

amazon.com

51–60 of 768 posts

Re: I'm sorry but I cannot fulfill this request it goes against OpenAI use policy

#51

What is that? An AI generated title on AI generated images? For $325?

Dropped shipped item probably from here: https://www.vidaxl.com/e/vidaxl-sideboard-18.5%22x13.8%22x29...

That's decent mark up. I bet I could write an app to take products from that site, post them to Amazon, and then just drop ship the orders for me. Of course, I'd have to write all those descriptions...

Re: I'm sorry but I cannot fulfill this request it goes against OpenAI use policy

#53

I get that this is basically fraud and spam, but this should really highlight the dangers of letting an unattended LLM do anything for your company at all. It can, and will, fuck up dramatically sooner or later.

>> unattended LLM do anything for your company at all. It can, and will, fuck up dramatically sooner or later. So, just like any other random employee?

No. Random employees have a well-understood distribution of mostly normal human errors of certain types and estimated severity, relative to unattended LLM which has a poorly-understood distribution of errors in both type and severity. (“SolidGoldMagikarp”.)

Re: I'm sorry but I cannot fulfill this request it goes against OpenAI use policy

#55

Easy fix since ChatGPT always apologises for not complying: any description or title containing the word "sorry" gets flagged for human oversight. Still orders of magnitude faster than writing all your own spam texts.

Sometimes it "apologizes" rather than saying "sorry", you could build a fairly solid heuristic but I'm not sure you can catch every possible phrasing.

OpenAI could presumably add a "did the safety net kick in?" boolean to API responses, and, also presumably, they don't want to do that because it would make it easier to systematically bypass.

Re: I'm sorry but I cannot fulfill this request it goes against OpenAI use policy

#56

Earlier quoted context omitted.

>> unattended LLM do anything for your company at all. It can, and will, fuck up dramatically sooner or later. So, just like any other random employee?

not THAT badly, lol

People on this forum often "joke" about dropping the production database as a rite of passage for noobs

Re: I'm sorry but I cannot fulfill this request it goes against OpenAI use policy

#57
post #6

I wonder what they're prompting ChatGPT with, and what policy it violates. I asked the standard, free ChatGPT 3.5 > Please generate a product title to be used on an e-commerce site for a chest of drawers with three drawers, a metal frame, and a butcher block top and it responded with > "Modern Metal-Frame Chest of Drawers with Butcher Block Top - Three Drawers Storage Solution" which would be a fine title for this li…

> I wonder what they're prompting ChatGPT with

"Please generate a title to be used to sell a lovely, large chest with a slender frame and three willing receptacles."

Re: I'm sorry but I cannot fulfill this request it goes against OpenAI use policy

#58
post #54

Ah, FOPEAS, that distinguished brand of kitchen counter drawers renowned throughout the world.

Amazon, in general, is not the place to shop for "brands renowned throughout the world."

Most of those folks stay off amazon, and If you're lucky enough to find such a brand on Amazon the chances that you receive a counterfeit version are pretty great.

Although if I had an endless bag of money to burn it'd be fun to buy an Amazon Rolex [0] just to see how it's handled.

[0]: https://www.amazon.com/Rolex-Oyster-Perpetual-Master-116710B...

Re: I'm sorry but I cannot fulfill this request it goes against OpenAI use policy

#60

I get that this is basically fraud and spam, but this should really highlight the dangers of letting an unattended LLM do anything for your company at all. It can, and will, fuck up dramatically sooner or later.

>> unattended LLM do anything for your company at all. It can, and will, fuck up dramatically sooner or later. So, just like any other random employee?

The employee generally knows they fucked up and can escalate the issue. Discussion on whether or not this actually happens will follow in comments below.
Post reply on HN