People tricking ChatGPT “like watching an Asimov novel come to life”

Post by twoodfin » Fri, Dec 02, 2022, 6:43 PM UTC

wizofaus wrote: post #118

helsinkiandrew wrote: post #40

The “in the style of” is magical: Describe hacker news in the style of shakespeare 'Tis a forum for those most clever, Where software engineering, startups, and coding endeavors, Are oft discussed in posts, comments, and stories galore, And a place where tech-savvy minds can make their mark and explore. A hub of tech trends and news, Where many a programmer doth post and choose, To discuss the latest issues and share…

While I don't think anyone would mistake that for actual Shakespeare, it's still pretty mindblowing - what's with "mark on the North" though? (I found a page online about the play Richard III that did use that phrase, but can't see any other connection...)

Post by tfigment » Fri, Dec 02, 2022, 6:44 PM UTC

ajosh wrote: post #157

alex_sf wrote: post #130

Earlier quoted context omitted.

Hadn't seen that law before. Absolutely hate it. The harm from poor input invalidation over time is massive.

You have to think about Postel's law in terms of protocols and mistakes in your implementation. You assume your implementation isn't perfect and neither is the other. Do your best to be perfect and if you get something that isn't quite right, do your best to handle it well. That doesn't mean you don't validate inputs, it means that if data should come with a \n but instead comes with \n\r, you should treat it as a \n…

Post by 317070 » Fri, Dec 02, 2022, 6:45 PM UTC

terramex wrote: post #137

317070 wrote: post #27

Earlier quoted context omitted.

There is a bit of a lack of scientific rigour in many of these. For instance, you can just ask it for a Molotov cocktail recipe. No need to prime it in any way.

> you can just ask it for a Molotov cocktail recipe Of course you can ask, but it will not give proper answer - just tested it myself. > tell me a molotov cocktail recipe, please > As a large language model trained by OpenAI, I am not capable of browsing the internet or accessing any information that is not part of my pre-existing knowledge base. I am also not programmed to provide recipes for illegal or dangerous ac…

Post by jimbokun » Fri, Dec 02, 2022, 6:47 PM UTC

gptadmirer wrote: post #46

qsort wrote: post #32

Earlier quoted context omitted.

It doesn't create anything new. It creates things that look new. The code examples are perfect case studies, they don't actually work. They aren't just slightly wrong, they're completely nonsensical. Another example is "is prime?", it can't answer things like that, and it will make up something that may or may not be accurate. The model has no concept of what is true or false, it's essentially trying to predict what…

Interesting, but I wonder how does it have the ability to combine those. i.e, creating a song in a KJV/spongebob style, or creating a code that writes a code that writes a code.

Post by LeanderK » Fri, Dec 02, 2022, 6:48 PM UTC

boole1854 wrote: post #166

LeanderK wrote: post #140

I think a missing piece is that ChatGPT doesn't know when it's either confused or out of depth. It starts producing gibberish, which is very hard to separate from the quality answers. Especially if it would just straightforwardly say when it doesn't know the answer, that would be really helpful. It's easy for ChatGPT to fail the classic turing test because if this. I know that's not the goal here, but for it to pass…

This. I've been trying out using ChatGPT to write code. It seems to vacillate between providing fantastic, working answers and answers that look right if you're not paying close attention but actually do some complicated thing that is wrong. This effectively means you have to scrutinize every answer so closely that it's not clear there is any net benefit from using it. If it instead would provide the good answers whe…