Hacker News Reader

Comment by rushingcreek | Hacker News Reader

Phind founder here. You can try the model for free, without a login, by selecting Phind-70B from the homepage: https://phind.com.

View on HN

I don't use LLMs a lot, maybe once a week or so. But I always pick Phind as my first choice because it's not behind a login and I can use it without giving my phone number. Hopefully you'll keep it that way!

I don't see how they could. They need to finance it at some point?

they are already financing it, there are 2 paid plans [0]. For THAT, you need an account (but no phone number).

[0] https://www.phind.com/plans

I think there’s room in the market to subsidize real users. Phind delivers absurd value, so I think the majority of paying users could account for the tech-averse or privacy-conscious

https://labs.perplexity.ai is the same and it loads much faster than Phind.

Important and hard-hitting question from me: have you ever considered calling yourself the Phinder or the Phiounder?

or the PhiTO / PhiEO

Find Phounder

Phindational models, phintech, Phinterest, phinder… it might be the best startup name of all time. Hell, startup a password manager and call it Phinders’ Keeper.

Pour one out for Phabricator.

And here I was wondering why this service was called pee-hind!

It seems unexpected that other people can edit a link to a Phind chat just by getting the URL. It means that if you share a URL with someone, they can change your results: https://www.phind.com/search?cache=k56i132ekpg43zdc7j5z1h1x

Very nice. I've been working with GPT4 since it released, and I tried some of my coding tasks from today with Phind-70B. The speed, conciseness, and accuracy are very impressive. Subjectively, the answers it gives just feel better than GPT4, I'm definitely gonna give pro a try this month.

I prefer Phind's web search with LLM to both Google search and GPT-4. I have switched my default search engine, only using Google for finding sites, not for finding information anymore.

GPT-4 might be a better LLM but its search capability is worse, sometimes sends really stupid search keywords that are clearly not good enough.

I won’t steal phind’s thunder but kagi is another great modern tool to have, and much more reliable than google for a technical user IMO. Obviously Phind is irreplaceable for complex or chat-based technical questions, but Kagi sees much more use from me daily for syntax stuff, Wikipedia searches, finding and relating papers, etc.

Any chances of an API?

And are there plans to release any more weights? Perhaps one or two revisions behind your latest ones?

Ask phind to make you one that screen scrapes

I tried asking "What is the size of Phind-70B's context window?" and it couldn't answer the question. Strangely, it immediately found the page with the answer (https://www.phind.com/blog/introducing-phind-70b) but refused to acknowledge that the answer was there. I tried asking several ways. It even quoted the exact answer in the displayed snippet, but still said there was no answer!

Here are a couple screenshots:

https://imgur.com/a/u7iKOyw https://imgur.com/a/aHAto5H

And here's the link to the whole conversation:

https://www.phind.com/search?cache=zlaksmzkm0h5cpx8l95n62tl

Why is this happening? Does it generally have difficulty with reading web pages, or is there something strange about this particular question?

Since you're here: have you considered moving to other, better generalist base models in the future? Particularly Deepseek or Mixtrals. Natural language foundation is important for reasoning. Codellama is very much a compromise, it has lost some NLP abilities from continued pretraining on code.

I tried a question about Snobol4 and was impressed with what it said (it couldn't provide an exact example due to paucity of examples). When testing more mainstream languages I have found it very helpful.

I'm selecting 70B and it is coming back with "Answer | Phind-34B Model".

I'm not sure if it's really using the 34B model or if the UI is wrong about which one it used

You have to click on the "Chat" option at the top left corner, then it'll use the 70B model. I got stuck on that too til I figured that out.

Please try logging in in that case, you will still get your 10 free uses.

Hello Michael, lovely to see this, congrats. Do you already have an API? I could not see it on the site. If not, then do you know around when we can expect it? I am building a desktop BI app with hosted and local LLMs (need schema inference and text to SQL). Would be nice to have Phind as an option for users. Thanks

This is good stuff, congrats. Took a little detour, but GPT-4 does too (https://www.phind.com/agent?cache=clsxw1mru0033l908mojpvb3b)

Why do none of the graphs show the speed difference? That seems to be your biggest advantage and the subject line...

Hmm, when I try I see this in the dropdown:

0 Phind-70B uses left

And I've never made any selection there.

I'd suggest logging in in that case -- you will still get your free uses. The Phind-70B counter for non-logged in users has carried over from when we offered GPT-4 uses without a login. If you've already consumed those uses, you'll need to log in to use Phind-70B.

Thanks.

Are you considering adding more non-US payment methods for Phind Pro?

For sure this. I've recently found out that you can only pay using credit card, US bank account or Cash App.

API on the horizon?

Hi, when I try to use the 70B model from the homepage, the response indicates that it's using the 34B model.

Please try logging in in that case. You will get 10 free daily 70B uses.

Reply on news.ycombinator.com