Hacker News new | ask | show | jobs
by layer8 1324 days ago
From one of the replies: “This is awesome. I also love how 20% of the zip codes are wrong. Messy AI future seems really fun and chaotic.”
5 comments

You need an AI that can understand when not to answer as opposed to some best effort guessing. Some of that input didn't have numbers in the right format so no zip code.

The hilarious one is changing the zip code to 90210. The AI basically accusing you of a typo because you obviously meant that more famous zip code.

General purpose AIs in situations where more targeted, simpler solutions are needed are going to be incredibly dangerous. Sure this AI can fly a plane 99.999% of the time, but every once in a while it does a nose dive because of reasons we cannot possibly understand or debug.

A human developer once told me that bad data is better than no data. <facepalm>

So of course a human developer made an AI that makes bad data.

FWIW, the actual saying is that for the purposes of collection by enemies (like Facebook and Google or KGB and NSA), the only thing better than no data is bad data.
FWIW, I was told that well before Facebook was a thought in the Zuck's head. Pre-socials, nobody shared data like is done today, so the NSA had to actually work to get it. Kids these days... /s
The author posted a follow up using a more advanced (and expensive) gpt3 model (davinci) which does a better job of parsing out the zip codes. It generally does a better job at everything, but if you can get away with one of the less expensive models then all the better.
yeah, most of these demos for GPT-3 are that go viral are cherry picked at best
>I also love how 20% of the zip codes are wrong.

Only they aren't. Check the video again, they come out fine.

Edit: Oh dang, you're all right, several of them have wrong digits. :l

What are you talking about? Look at 27 seconds into the video. Many of the zip codes are wrong.
Row 15 includes the zip code 92105 in column A but the output is 92101. Similar for Row 5.