Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
CSMastermind
on Oct 24, 2023
|
parent
|
context
|
favorite
| on:
OpenAI Finally Allows ChatGPT Complete Internet Ac...
Do you know what model perplexity uses under the hood?
I just tried it out with my normal test queries and found it to be far worse than Google's Bard.
moffkalast
on Oct 24, 2023
|
next
[–]
To be fair, Bard has massively improved recently and can in my brief experience even outperform 3.5-turbo for lots of things.
behnamoh
on Oct 24, 2023
|
parent
|
next
[–]
Except that it still has a short ctx size.
brianjking
on Oct 24, 2023
|
prev
|
next
[–]
I'd disagree by far. I use Perplexity as my main search engine and am a paid subscriber. Copilot with GPT-4 or Claude is fantastic.
13rac1
on Oct 24, 2023
|
prev
[–]
Paid accounts can use the Perplexity LLM, GPT-4, or Claude 2.
Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
I just tried it out with my normal test queries and found it to be far worse than Google's Bard.