Live data from Hacker News

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

amazon.com

231–240 of 768 posts

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

#231
post #92

Earlier quoted context omitted.

Sometimes. https://news.bbc.co.uk/2/hi/7702913.stm

I brought up translation as a risk with a friend. If you pay someone for a translation these days, there is a chance they will just feed it to some AI to cut costs. You'll have no way to validate yourself if you don't speak the language.

Just a chance? I routinely translate hundred pages of pdfs to greek, in 3 minutes. The translation is far from perfect depending the text and it still needs a human in the loop for corrections, but i couldn't imagine translating a 300 pages pdf to greek by hand.

There is also the translaxy bot on poe.com which i use to translate english or modern greek to ancient greek. Out of this world good translation.

I mean, are humans still employed to translate text? Like an employee doing that job, and only that?

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

#233
I bought a headset. it turned out not to support Bluetooth. upon wanting to return the headset, they set it would not be possible. that was until I found a line in their listing that said it should support Bluetooth.

I am quite sure that line cam. in because somebody just copy pasted the wrong file to the listing.

the merchants will be liable for what they let the LLMs promise on behalf of them.

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

#234

Using Amazon for shopping is terrible, borderline unusable in 2024. They're hard to compete with because they're giant and have an amazing logistics network, but it also seems like there's a big vacuum in the market for an "everything store" that's actually good.

As someone who uses Amazon regularly, we live in different worlds. My experience is pleasant and straightforward; I get what I want and it arrives quickly.

Your comment reads just like the reviews. Worthless

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

#235

Earlier quoted context omitted.

Yeah we must. Nothing I but from Amazon is what I expect and top that off with it arrives late despite me paying for prime. I ordered a blender last week that doesn’t even blend, which I only realized after I had loaded it up with stuff to make a smoothie. When things show up and actually are what I expect based off of the image and they work right it is a rare surprise.

Counting it up, I've ordered 58 times from Amazon in 2023 and every single item was exactly what I asked for, and arrived within a few days. I wonder why we're having such wildly different experiences...

I think Amazon is a good platform to buy from when you know exactly what you want, or when you are good at researching and weeding out the crap. People who explore products on Amazon and make quick purchases, or impulsive shoppers in general probably have a bad time.

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

#236

Using Amazon for shopping is terrible, borderline unusable in 2024. They're hard to compete with because they're giant and have an amazing logistics network, but it also seems like there's a big vacuum in the market for an "everything store" that's actually good.

I'd really like a more 'curated' or vetted everything store. I don't need to see 40 of the same exact item rebranded into various English horrors. Walmart seems most primed to do this, barring third party sales. Or Sears, if they ever had a miraculous turnaround to their old days.

There are more listings like that one, some are sold by Amazon. https://amzn.to/41Zf3hS

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

#237

Using Amazon for shopping is terrible, borderline unusable in 2024. They're hard to compete with because they're giant and have an amazing logistics network, but it also seems like there's a big vacuum in the market for an "everything store" that's actually good.

I'd really like a more 'curated' or vetted everything store. I don't need to see 40 of the same exact item rebranded into various English horrors. Walmart seems most primed to do this, barring third party sales. Or Sears, if they ever had a miraculous turnaround to their old days.

Rebranded .. I'm getting really annoyed with the same product, different prices, different brand names apparently generated by some China-based anagram generator

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

#238

Earlier quoted context omitted.

As someone who uses Amazon regularly, we live in different worlds. My experience is pleasant and straightforward; I get what I want and it arrives quickly.

Yeah we must. Nothing I but from Amazon is what I expect and top that off with it arrives late despite me paying for prime. I ordered a blender last week that doesn’t even blend, which I only realized after I had loaded it up with stuff to make a smoothie. When things show up and actually are what I expect based off of the image and they work right it is a rare surprise.

If this were happening for everyone, Amazon would have a stock market reckoning.

You might be buying off-brand stuff.

But what you'd find at Target or Microcenter, and you'll have a good time.

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

#239
post #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.

> 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.

Is a safety net kicking in or is the model just trained to respond with a refusal to certain prompts? I am fairly sure it's usually the latter, and in that case even OpenAI can't be sure a particular response is a refusal or not.

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

#240
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…

Using the words "black dresser" or "brown dresser" maybe?

Or big brown/black cross dresser?
Post reply on HN