Ask HN: What's Your Take on Perplexity AI?

[zyruh]

Perplexity has been growing fast as an AI search tool, blending conversational answers with cited sources and real-time web data. I’m curious how the HN community sees it:

Do you use it regularly, and if so, what makes it stand out from other LLMs or search engines?

How do you feel about the quality, speed, and trustworthiness of its answers?

Are there any drawbacks, limitations, or dealbreakers you’ve noticed?

Interested to hear both positive and critical perspectives—especially from people who’ve tried it alongside tools like ChatGPT, Claude, or Kagi.

[supasend]

I use it mainly for web search and have been using it for 2 years. Based on my experience, it currently hallucinates less than before. Selection between models make a difference over other apps.

[ctbellmar]

I had some time for in depth experiments with it this summer and was disappointed. It gets the surface level details alright, but falls apart on any detailed work.

Examples that failed: - opening hours for POI (restaurants, tourist attractions, etc) - mostly made up - GPS coordinates - produced results that were nearly 100% inaccurate - finding contact info (e.g. phone, email) for specific government or public bodies - nearly 100% inaccurate

The issue with above was mainly not a lack of results but rather fabricated/made up ones. As in: here are the coordinates (that don't correspond to actual locations) or here are the phone numbers of such and such departments (that don't exist), creating more work to try and discover they are nonsensical vs. just giving "no results found" message.