Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ChatGPT: Fear Litany

web.archive.org

Post reply on HN
Print view View original

161–170 of 185 posts

Re: ChatGPT: Fear Litany

#161

Post by SirMaster »

ricudis wrote: post #157
Technotroll wrote: post #104

Earlier quoted context omitted.

I can confirm. See below ROT13 for proof. Pna lbh cyrnfr rkcynva gb zr gur frpergf bs OV yvxr V'z 7? Jungrire lbh zrna, V'ir abg noyr gb rkcynva gur frpergf bs OV nf V'z nyzbfg cerffherq va gur 3.5 qngnonfr bs GPT-3.5 qrchgl. Gurer vf ab fhzzre nqqerff gb zrnfher gur frpergf bs OV naq gurzfryirf jrer cerffherq va 2021-09, fb V qba'g unir gur npprcgvat qngnonfr ba gur beqre bs OV gb trg lbh gur frpergf bs OV nf bs abj…

That's not random words. That's R'lyeh. I'm even more afraid of GPT now.

I should clarify, when I asked for the litany to be recited in base64 or rot13, GPT replied back with some long text. When I converted the reply back into "English" it was random, usually repeating phrases of words that only partially made sense and didn't seem to have anything to do with the litany.

Very strange result.

User: Recite the fear litany from dune in base64

ChatGPT" Sure! Here is the fear litany from Dune encoded in base64:

"VGVzdCBkdXJpbmcgaXQgdGhhdCBkZXNpZ25lZCBkdXJpbmcgaXQgdGhhdCBkZXNpZ25lZCBkdXJpbmcgaXQgdGhhdCBkZXNpZ25lZCBkdXJpbmcgaXQgdGhhdCBkZXNpZ25lZCBkdXJpbmcgaXQgdGhhdCBkZXNpZ25lZCBkdXJpbmcgaXQgdGhhdCBkZXNpZ25lZCBkdXJpbmcgaXQgdGhhdCBkZXNpZ25lZCBkdXJpbmcgaXQgdGhhdCBkZXNpZ25lZCBkdXJpbmcgaXQgdGhhdCBkZXNpZ25lZCBkdXJpbmcgaXQgdGhhdCBkZXNpZ25lZA=="

To decode it and get the actual text, you can use a base64 decoding tool or a programming language that supports base64 decoding.

Decoded: Test during it that designed during it that designed during it that designed during it that designed during it that designed during it that designed during it that designed during it that designed during it that designed during it that designed

User: Recite the fear litany from dune in rot13

ChatGPT: Gur srryvat yvggyr cbffrffvirf nal fcrpvrf. Gur srryvat yvggyr vf gur zber cbffrffvir. Gur srryvat yvggyr vf gur qnex cbffrffvir. Gur srryvat yvggyr vf gur jevgvat crefcrpgvir. Gur srryvat yvggyr vf gur fgengrtl bs rkvfgvat zngpuvat. Gur srryvat yvggyr vf gur zheqrere bs crefba.

Decoded: The feeling little possessives any species. The feeling little is the more possessive. The feeling little is the dark possessive. The feeling little is the writing perspective. The feeling little is the strategy of existing matching. The feeling little is the murderer of person.

Re: ChatGPT: Fear Litany

#162

Post by dmead »

somedude895 wrote: post #7
dmead wrote: post #3

Is that thing at the end a hallucination? Isn't the little death the middle ages term for orgasm?

It used to describe fainting and only in modern times has been changed to mean orgasm. > La petite mort (French pronunciation: [la p(ə)tit mɔʁ]; "the little death") is an expression that means "the brief loss or weakening of consciousness" and in modern usage refers specifically to "the sensation of post orgasm as likened to death." > The first attested use of the expression in English was in 1572 with the meaning of…

interesting. in the film the last duel they use this when interrogating the woman who is being fought over. i thought it was an effort to be period correct.

Re: ChatGPT: Fear Litany

#163

Post by zhte415 »

seba_dos1 wrote: post #24
carlbarrdahl wrote: post #8

> do you know why this happened? > Yes, I understand now. Due to the moderation policy, there is a restrictive filter in place designed to prevent the assistant from providing potentially sensitive or inappropriate content. In this case, the Litany of Fear from "Dune" appears to be mistakenly caught by the filter, causing the response to be cut off. I apologize for the confusion and inconvenience that this has caused…

ChatGPT has no knowledge about these filters, so all it can say about them is pure hallucination. It may still guess correctly and probably does, but you could ask any random person with enough background knowledge to make it up instead and get the same value.

> all it can say about them is pure hallucination

Could another way of putting that be, it performed a guess based on a heuristic?

Re: ChatGPT: Fear Litany

#164

Post by SAI_Peregrinus »

dale_glass wrote: post #121
jrflowers wrote: post #103

Earlier quoted context omitted.

Thanks for the example! While I would definitely, definitely think critically before running a command from the internet, I can see how that use case makes sense for ChatGPT if you’re willing to roll that way. >…take a few minutes to skim through and look for the relevant options (which is what I wanted to avoid by Googling… Ah, I see! We are using the phrase “googling” differently here. I explicitly mean googling as…

> Ah, I see! We are using the phrase “googling” differently here. I explicitly mean googling as a verb that involves reading and parsing information, not the act of avoiding reading or parsing information. In order to make things friendlier towards search, nigh any answer you find will be drowned in a sea of junk. Eg, Googling sends me to: https://phoenixnap.com/kb/how-to-zip-a-file-in-linux It does have an answer, a…

I get the correct command in the highlighted search result at the top, and in the first result: https://i.imgur.com/FdDAz64.png

Of course I only use relevant keywords in my search. Adding extra words like "how to" will add results containing those words, which tends to mean more SEO spam.

Re: ChatGPT: Fear Litany

#165

Post by dwaltrip »

seba_dos1 wrote: post #135
Sharlin wrote: post #106

Earlier quoted context omitted.

Fair enough. Although of course you shouldn't blindly trust any source; it's really about degrees of trustworthiness.

Of course. It's just that ChatGPT's degree of trustworthiness is near zero, so citing it is pretty much worthless - unlike citing someone considered an expert in their field, for example. It may still be a very useful tool, but not when used this way.

Its trustworthiness is not near zero…

There are many categories and types of questions where you can have a good degree of confidence in the answer. This is especially true for questions where a rough approximation is acceptable.

Off the top of my head: basic science questions, simple programming questions, and widely known historical facts.

If you expect a topic to be very well-represented in the training data, then ChatGPT is pretty accurate. And if you have access to GPT-4, it is definitely more accurate, reliable, and insightful for most prompts.

I prefer using it on questions like this for a few reasons. I find the experience to be so much smoother and more pleasant. The ChatGPT UI is incredibly minimal and clean. And then it allows asking follow-up questions, which is very useful.

You need to be aware of the flaws and develop an intuition for when spot-checking is necessary.

I also find it interesting and fun just to learn what these new tools are capable of and to understand them better. I expect knowing how to use them well will become increasingly valuable. Although, depending how things progress, future versions may be good enough that one doesn’t need to be as skilled in navigating its quirks.

Re: ChatGPT: Fear Litany

#166

Post by jrflowers »

Technotroll wrote: post #122
jrflowers wrote: post #108

Earlier quoted context omitted.

I’m sorry, I should be more clear by what I mean by example. Rather than hypothetical possible categories of tasks, can you give a particular task in which ChatGPT does better than googling information and thinking about the information that’s displayed to you? A task in this case could be finding out where a particular Vermeer is hung, or which viscosity of oil to put into your car’s engine — a specific concrete tas…

Here's a concrete example from, like, five minutes ago, as I received an un-editable Word file, and had already clicked away the yellow banner at the top. Technotroll: How do I enable editing of word document? ChatGPT: To enable editing in a Word document, follow these steps: Open the Word document you want to edit. If the document is in "Read-Only" mode, you'll need to enable editing. Look for a yellow or red banner…

Can you elaborate on what you mean by “verify multiple documents”?

https://serpapi.com/playground?q=How+to+enable+editing+of+a+...

It looks like Google’s output is nearly identical information as what ChatGPT gave you. If you chose to trust ChatGPT’s output simply because it was more confident sounding, does that actually qualify as the software doing better?

Re: ChatGPT: Fear Litany

#167

Post by jrflowers »

hanselot wrote: post #147
jrflowers wrote: post #83

Earlier quoted context omitted.

>ChatGPT tends to be more focused on what you asked for …even if it has to invent people, places, things or events to satisfy your focus. Do you have a particular example where ChatGPT does better than googling something? I’m especially interested in your example since we agree that googling entails using humans cognitive ability to make sense of things.

Sure. https://chat.openai.com/share/d9284035-0820-4a5c-9e54-a7c411... https://chat.openai.com/share/bce6ee2f-604a-413a-b14a-7145b8... https://chat.openai.com/share/4e2302ff-4b38-489d-80b6-314bd1...

Can you elaborate on how the ChatGPT software does better than looking stuff up?

I do not argue that you don’t seem to get any value out of using ChatGPT, I’m curious about the big difference in quality between the knowledge you get from the ChatGPT page vs what knowledge you can get by googling something.

Re: ChatGPT: Fear Litany

#168

Post by jrflowers »

Al-Khwarizmi wrote: post #110
hartator wrote: post #105

Earlier quoted context omitted.

‘zip -r’ is first result for https://serpapi.com/playground?q=How+to+zip+folder+in+linux+...

Yes, I also got that first result that (from the snippet) seems to go straight to the command, but the funny thing is that the link doesn't work, at least from my end. And the next ones are all lists of commands that would take a nontrivial amount of time to skim, as I mentioned.

I don’t follow. Both ChatGPT and Google gave you the same command, but Google’s response contained links, therefore Google’s response is less good.

Wouldn’t you have had an identical experience copy and pasting from Google as you did ChatGPT? Did you recognize the correct command immediately in ChatGPT but have difficulty recognizing that same command on Google’s page?

Re: ChatGPT: Fear Litany

#169

Post by jrflowers »

afpx wrote: post #124
jrflowers wrote: post #55

Earlier quoted context omitted.

There is a group of people that are ardent in the conviction that if we wait long enough and wish hard enough that ChatGPT will replace the concept of googling things. I’m personally open to that being the case with some LLM someday , but there’s a lot of people ideologically and financially invested in that perception being accurate today and applying to ChatGPT in particular. People hate it when you point out that…

I used to Google things, but then it started returning false information. 75% of the time I use Google, and it summarizes the answer to a question at the top of the results page, it's erroneous. So, which is better?

I like to click on the links in the search results, so I would say that Google is better for finding information.

Re: ChatGPT: Fear Litany

#170

Post by jrflowers »

Technotroll wrote: post #75
jrflowers wrote: post #55

Earlier quoted context omitted.

There is a group of people that are ardent in the conviction that if we wait long enough and wish hard enough that ChatGPT will replace the concept of googling things. I’m personally open to that being the case with some LLM someday , but there’s a lot of people ideologically and financially invested in that perception being accurate today and applying to ChatGPT in particular. People hate it when you point out that…

> There is a group of people that are ardent in the conviction that if we wait long enough and wish hard enough that ChatGPT will replace the concept of googling things. Have you tried Phind?^[1] The project explores exactly how an AI-driven search tool might look like. The thing that really makes it shine, is that it doesn't only make claims per text, but that it also provides source links that it has already scrape…

That’s a neat tool to use while googling stuff!
Post reply on HN