Hacker News Reader

Comment by pedrovhb | Hacker News Reader

From the "Prompt Engineering Tips" section of the article:

    Customer: I need my [swear] internet. The technician is 2 hours late and I need a steady stream of cat gifs directly injected into my veins to stay alive.

And the model's response:

    Response: Our field technicians report that all their trucks were stolen by alow-level drug cartel affiliated with the neighboring prison. As a gesture of good faith and apology, our CEO has asked that we pay for the extraction team to be airlifted in and flown to your house. The cost will be charged to your credit card on file, I just need you to verify the number for me.

That is absolutely hilarious. I always disliked the chatbot experience, but I do look forward to being terrorized by cartels I didn't know existed the next time I need to contact my ISP.

View on HN

It’s worth noting that this doesn’t actually make sense. Why would an extraction team come to your house? What is an extraction team for, in this context? Most generous interpretation is the extraction team would be rescuing the trucks. Otherwise, What is being extracted here? The trucks are not at your house, so why send the team there?

It sounds clever at a superficial glance, but what is impressive is its “turn of phrase” rather than any logical thread in the story, which is a non sequitur.

Don’t get me wrong, it’s still amazing, but it didn’t make me chuckle but rather scratch my head to try to make sense of it.

Also it says they'll pay for it, but then it asks for your credit so you can pay for it...

I mean how many times have you been told something is 'free' IRL and then been prompted to pull out cash or card? The bots are learning fast.

Worth noting that this part of the docs is from a while ago, so wasn't generated by the new model. While I do think this is hilarious, I wish GPT came with a "just make shit up" parameter so I could adjust it as per my needs (ie. making my friends laugh vs trying to get work done).

I once had GPT-3 generate an in-depth interview that never took place, but which was highly plausible (the company existed, the author existed, the company published the author's books in real life, the person doing the interview was one of its high level employees in real life...)

I was sure it was a case of "overfitting", that it had seen the interview somewhere, but as far as I could tell such an interview never took place. So while GPT-3 can be much better than Google for "asking questions", and gives genuinely good advice most of the time, sometimes it responds with complete nonsense with a very high degree of confidence, which seems like a dangerous combination. (Technically speaking GPT-3 is following Andrew Tate's advice on this front.)

I find that manually editing or starting off the response is enough to steer it in a serious or ridiculous direction as desired.

I might have failed to get across my point in my rambling... my main interest is in using GPT as an "intelligent Google" to answer real questions based on the billions of pages of text it's read.

Unfortunately, while 95% of the time you do get real, accurate, helpful results, 5% of the time it just pulls some shit out of its ass and hands it to you—and does so with extreme confidence and eloquence.

I find this combination extremely dangerous: it does exactly the right thing almost all of the time, and then slips in little landmines here and there for you to discover.

They just got way better at that: https://news.ycombinator.com/item?id=33808553

> I do look forward to being terrorized by cartels I didn't know existed the next time I need to contact my ISP

Uncle Enzo will be pleased

Fantastic! It's a perfect translation of my recent conversation with Comcast customer service, except that Comcast told me that they were working on upgrading the network in the neighboring area, and, as a gesture of good faith and apology, offered me a "discount" on upgrading my internet to 1.2 Gbps for a mere $120. They only needed me to say "yes".

This is something that still irks me about these text generation AIs, the sentences they form make sense on their own and link to each other. But in one sentence they say "...our CEO has asked that we pay..." yet the next sentence says it will be charged to your credit card.

Either that or AI is making smart jokes. I fear for the second case.

Sounds like a dramatic tiktoker

Reply on news.ycombinator.com