Live data from Hacker News

Show HN: Find AI – Perplexity Meets LinkedIn

usefind.ai

11–20 of 78 posts

Re: Show HN: Find AI – Perplexity Meets LinkedIn

#11

Trying to get a sense of whether the results really are good by testing it on a query I basically know the answers to for my niche, but it looks like to get more than 3 results I've got to join the $39/mo plan. Is that the case?

Yes, but if you share or email me the link I'll redo the search run to completion.

There's a pretty high cost to run each search. So, even offering partial searches to logged-out users is pretty expensive for us.

Re: Show HN: Find AI – Perplexity Meets LinkedIn

#13

How do you opt your LinkedIn or other personal info out?

Send an email to the support email at the bottom of the page. Like Google, all the data here is from public sources - we're just indexing it.

Are people on LinkedIn with profiles set to private indexed?

Re: Show HN: Find AI – Perplexity Meets LinkedIn

#14

Earlier quoted context omitted.

What are some of the other verticals you're considering. What types of data sources are you using?

> What are some of the other verticals you're considering? Thinking of VCs and finance next, because lots of the user so far have been customers. Law is high on the list. Healthcare has been something are interested in, too. > What types of data sources are you using? It's all scraping and LLMs under the hood. Nothing secret, but there's some surprising sophistication to how it works. We have ~50k companies and ~100k…

Thanks for the response. I think Tech/VCs/Finance are all pretty well correlated, you might want to consider branching out of that bubble of the world IMO.

Re: Show HN: Find AI – Perplexity Meets LinkedIn

#15

What vectordb are you using? guessing you're just slammed with traffic right now, but it says it searched 1.4k records and it took over 2 minutes. Should be able to run it subsecond.

We're using PGVector.

The way it works is that we use some heuristics to find candidates for your search. That's the 1.4k number you see - and that does take milliseconds. Then, we go through and analyze each candidate individually with an LLM. So, that's 2 minutes that it ran ~1.4k calls to OpenAI.

Re: Show HN: Find AI – Perplexity Meets LinkedIn

#16
> We're sorry, but something went wrong.

> If you are the application owner check the logs for more information.

Console:

cable_stream_source_element.js:22

       GET https://usefind.ai/searches/are-unhappy-with-robotic-process-automation-tools 500 (Internal Server Error)

Re: Show HN: Find AI – Perplexity Meets LinkedIn

#18
post #16

> We're sorry, but something went wrong. > If you are the application owner check the logs for more information. Console: cable_stream_source_element.js:22 GET https://usefind.ai/searches/are-unhappy-with-robotic-process-automation-tools 500 (Internal Server Error)

Sorry, under some serious load right now. Just increased all the server sizes and boosted the DB size.

Can you reload or try again?

Re: Show HN: Find AI – Perplexity Meets LinkedIn

#19

Search was "Find companies that are looking for designers with a print background." Result was: "We have analyzed 1072 candidates and found 0 records matching the search criteria." Why would you analyze _any_ candidates if the query was to find companies?

We have a database of ~50k companies right now. When you initiate a search, we identify "candidates" out of there to analyze for you. So, "candidate" is more of an internal word - we can update the designs to make that clearer. Then, we go through each candidate one-by-one to find matches.

Re: Show HN: Find AI – Perplexity Meets LinkedIn

#20
post #16

> We're sorry, but something went wrong. > If you are the application owner check the logs for more information. Console: cable_stream_source_element.js:22 GET https://usefind.ai/searches/are-unhappy-with-robotic-process-automation-tools 500 (Internal Server Error)

Sorry, under some serious load right now. Just increased all the server sizes and boosted the DB size. Can you reload or try again?

Thanks! Unfortunately same result
Post reply on HN