Hacker News Reader

Comment by codethief | Hacker News Reader

I'm really quite… perplexed by how so many people seem to be happy with Perplexity. I have tried it a number of times and it always hallucinated a ton (especially the stuff where it provided "sources").

View on HN

It uses only google as a backend, and the answer engine is based on the ancient llama 3.3 70B.

It's well behind Kagi (which uses a bunch of sources for results and new models for quick answer or assistant). Perplexity is even well behind other competitors like chatgpt

Ok ok, I'm signing up for Kagi now

Perplexity Pro allows you to use GPT-4 Omni, Claude 4 Sonnet, Gemini 2.5 Pro, Sonar, DeepSeek R1, and others. Can you clarify what you mean by based on the ancient llama 3.3 70B? And they pull results from multiple search engines, and their own index, not just Google.

Preference doesn't have to be based on anything, but providing misinformation that is easily verified is not that common on HN. And Perplexity Pro is different than vanilla Perplexity.

I was talking about their sonar API and what you get when you go to perplexity.ai and search by default -- it's llama 3.3 70B hosted with cerebras. Which is fast, but way way behind the times -- it's more likely to hallucinate than models from basically anyone from the competition, including quick answer.

You're right though it seems that they don't just use bing + their own crawler, but who else they use seems to be community speculation.

same, so much so that I almost think they have a bot army for astroturfing, because I cannot believe anyone gets value from it over just one of the main providers and google. They dont index data nearly as much or as often as google, they basically are at a pareto frontier of just serving the most amount of people with lean indexing based on fact that people look up a lot of the same things. It reminds me of looking at google earth where you can see cities have 3d models but a random neighborhood where you grew up would be images years old. So yeah, its useful but definitely not a replacement for google, so idk why anyone would pay for it.

Society is screwed once AI companies reach the 'using our product as our personal bot army' phase.

So in your opinion, incidentally in this thread about Kagi, you think Google is better? You imply Perplexity only uses their own index, but they pull results from multiple external search engines and their own index. As I mentioned in another thread, that kind of easy-to-verify-as-misinformation is not that common on HN. And Perplexity Pro is different than vanilla Perplexity.

Perplexity is something I had skepticism for but it (Perplexity Pro) has all replaced my talking to a neural net needs. i still use Google but their default ai responses annoy me so i avoid it these days, why is that spam there for me to process when searching is already a chore. The only complaint i have is the perplexity webapp is very slow on my older devices. It should switch to a lighter version if possible.

AI comments in general mean something different once versions are clarified. I've never seen so many comment threads where people don't specify clearly which version(s) they are discussing, which seems relevant 95+% of the time.

We only pump here sir.

Reply on news.ycombinator.com