Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Perplexity wins my AI race, published by Elizabeth on August 24, 2024 on LessWrong.
Perplexity is the first generalized AI chatbot I've found useful enough to integrate into any part of my daily workflow, much less across multiple domains. It speeds me up enough that I'm planning an increase in my freelancing rate.
Perplexity has three key advantages:
1. It provides citations, cleanly, in context
2. It has the persona of a sharp human instead of an intolerable customer service agent.
3. It is useful (and sufferable) across a wide variety of domains.
The citations are a bigger deal than they sound at first. I could of course google anything ChatGPT tells me and check the results, but that's costly. I have to spin up a new mental thread (and browser tab), sort through Google's increasingly shitty results, remember what claim I'm trying to check… the process eats up a lot of working memory at a time when it is scarce. If I wanted to trawl a sea of content farms I would have gone to Google in the first place.
Perplexity's high quality inline citations solve that . Want to check if a claim is justified? Click the number next to it and look for the relevant quote. Not a perfect substitute for a 30 hour literature search, but a lot of power per minute. I don't have to spin up a new mental thread, so the whole thing feels much lower friction.
Also thus far I've never caught it in a hallucination on a question of fact, although if real answers are scarce it will sometimes do the thing where it draws increasingly tenuous connections instead of just telling me no.
I also found perplexity easier to talk to while trying to learn some math and math history. It felt about as useful as my human tutor- better at some things, worse at others.
Test Questions
The real test was which AI do I find myself using, and the answer to that is definitively Perplexity. But just for fun or in case I was wrong, I ran a few questions Perplexity through all major engines to see what they said.
In all cases I used the top free model available. I have Perplexity Pro thanks to a promo, but I haven't ended up finding Pro to be much of an improvement. I do expect to use the pro-only PDF-analysis tool in the near future.
Comments from me are in italics and [brackets]
How do fractals relate to chaos theory?
I have a project investigating chaos theory as a case study in the development of scientific/mathematical paradigms. This doesn't require I become a mathematician, but I do need to understand how discoveries relate to each other and generally not be an idiot on the topic. Perplexity is my always available, infinitely patient tutor.
This should have been a challenging role for an AI to fill, because I have a friend who loves explaining math more than almost anything, and did his PhD in a related area. I even feel comfortable looking stupid in front of him. And yet Perplexity still had a value add, because it was never offline and I didn't feel a need to respect its time the way I would a friend's.
Perplexity (link to result including citations)
Fractals and chaos theory are closely intertwined concepts in mathematics and physics, with several key connections:
Self-Similarity and Complex Patterns
Fractals are geometric objects that exhibit self-similarity across different scales, meaning smaller parts resemble the whole. This property is often found in chaotic systems, where complex patterns emerge from simple rules.
Visualization of Chaotic Processes
Fractals frequently arise as visual representations of chaotic systems:
The Feigenbaum diagram, which illustrates population dynamics in chaos theory, displays fractal-like structures.
The Mandelbrot set, a famous fractal, is closely related to chaotic processes and can be used to visualize complex number behavior in iterative functions.
Characteristics of Co...
view more