Perplexity.ai prompt leakage

#1

Post by djoldman » Sun, Jan 22, 2023, 9:16 PM UTC

Perplexity.ai prompt leakage
twitter.com

Re: Perplexity.ai prompt leakage

#2

Post by babelfish » Mon, Jan 23, 2023, 5:51 PM UTC

You'd think the prompt would need to be a bit more engineered. How is ~100 words + a search results page a competitive advantage?

Re: Perplexity.ai prompt leakage

#3

Post by nadermx » Mon, Jan 23, 2023, 5:56 PM UTC

babelfish wrote: post #2

You'd think the prompt would need to be a bit more engineered. How is ~100 words + a search results page a competitive advantage?

Brevity is the mother of wit

Re: Perplexity.ai prompt leakage

#4

Post by unraveller » Mon, Jan 23, 2023, 6:03 PM UTC

i don't care how simply it's coded when it's so much better at cutting through the marketing speak that I use it for all my "what is X" questions instead of needing to go through multiple cycles of X vs (autosuggested alternative) pages on legacy search engines.

Re: Perplexity.ai prompt leakage

#5

Post by supermet » Mon, Jan 23, 2023, 6:05 PM UTC

    IF $prompt IN $output PRINT
    "You have been eaten by a grue"

Re: Perplexity.ai prompt leakage

#6

Post by dpflan » Mon, Jan 23, 2023, 6:08 PM UTC

How many businesses built on GPT are boiled down to bespoke prompts? I guess secured seed prompts are next feature for GPT…

Re: Perplexity.ai prompt leakage

#7

Post by maushu » Mon, Jan 23, 2023, 6:09 PM UTC

I wonder if they could change the prompt to prevent leaking the prompt and not ignore previous directions.

Re: Perplexity.ai prompt leakage

#8

Post by flutas » Mon, Jan 23, 2023, 6:11 PM UTC

They have to be pulling search results (and meta, like text) from somewhere and providing it to the prompt as well right? Otherwise I don't know how they are getting fresh data from GPT since it's cut off date is in 2021?

Also, after recreating this myself, it seems like the detailed option just changes the prompt from 80 words to 200.

Re: Perplexity.ai prompt leakage

#9

Post by firasd » Mon, Jan 23, 2023, 6:13 PM UTC

I don't think this kind of prompt leakage really matters from a strategy perspective. Pretty much every breakout internet biz in the past 20 years has been like "an HN comment poster can build that prototype". So what really matters is this thing is up live, it's being relatively widely used, it's integrated with Bing, it's pulling the right summaries of the search results into GPT's very length-constrained prompt context..

Here's yesterday's thread on this prompt context pattern: https://news.ycombinator.com/item?id=34477543

I've been experimenting with the 'gpt index' project https://github.com/jerryjliu/gpt_index> and it doesn't seem like "oh just put summaries of stuff in the prompt" works for everything -- like I added all the Seinfeld scripts and was asking questions like "list every event related to a coat or jacket" and the insights were not great -- so you have to find the situations in which this makes sense. I found one example output that was pretty good, by asking it to list inflation related news by date given a couple thousand snippets: https://twitter.com/firasd/status/1617405987710988288

Re: Perplexity.ai prompt leakage

#10

Post by eddsh1994 » Mon, Jan 23, 2023, 6:24 PM UTC

I just tried Perplexity and it's not very good. For example, ask it a question about a board game you play or how to write a modal in React that gives you a users input and its responses are inaccurate at best. For Ukraines latest news it just told me to check out Al Jazeera.