Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Phind-405B and faster, high quality AI answers for everyone

phind.com

Post reply on HN
Print view View original

101–110 of 163 posts

Re: Phind-405B and faster, high quality AI answers for everyone

#101

Post by Salgat »

TaylorAlexander wrote: post #11
sgc wrote: post #7

Earlier quoted context omitted.

I use it, with the phind models, instead of chatGPT. I had to change my user agent to Chrome since too many sites would refuse to work with FF otherwise, and now chatGPT is stuck in an endless captcha loop whenever I go there. I am just a casual user, to help write a quick script or to get some bit of relevant info. It works just as well or better for my use case, and of course having actual citations with links is w…

My friend has the endless captcha loop on ChatGPT too. Does anyone know how to fix it?

Incognito mode until it goes away on its own.

Re: Phind-405B and faster, high quality AI answers for everyone

#102

Post by druskacik »

CSMastermind wrote: post #99
rushingcreek wrote: post #93

Earlier quoted context omitted.

That’s great to hear! What are you asking it?

These are the types of questions I want to ask it: > What degrees are held by each of the current Fortune 100 CEOs? > What job did each of the current NFL GMs hold before their current position? > Which genre would each of the current Billboard Hot 100 songs be considered part of? > How many recipients of the Presidential Medal of Freedom were born outside of the US? > Which US car company has the most models in thei…

There is a method that could help immensely when answering questions like these. E.g. some of these question may be answered quite quickly using WikiData [0] (answer to question about the recipients of Medal of Freedom, query written with the help of Claude), instead of just scraping and compiling information from potentially hundreds of websites. I believe this idea is quite under-explored compared to just blindly putting everything to the model's context.

[0] https://query.wikidata.org/#SELECT%20%28COUNT%28DISTINCT%20%...

Re: Phind-405B and faster, high quality AI answers for everyone

#103

Post by dotancohen »

wokwokwok wrote: post #80
spirodonfl wrote: post #61

Earlier quoted context omitted.

Just to follow up on this: I asked it to give me a brief explanation on how to use laravel 11 blade fragments, which it did reasonably well. I then offered 3 lines of code of a route I'm using in Laravel and I asked to tell me how to implement fragment usage where the parameter in the url determines the fragment returned. Route::get('/vge-frags/{fragment}', function ($fragment) { return view('vge-fragments'); }); It…

Seems a little bit of an unfair generalisation. I mean, this is an unsolvable problem with chat interfaces, right? If you use a plugin that is integrated with tooling that check generated code compiles / passes tests / whatever a lot of this kind of problem goes away. Generally speaking these models are great at tiny self contained code fragments like what you posted. It’s longer, more complex, logically difficult th…

And you can have the LLM write the test, too.

Re: Phind-405B and faster, high quality AI answers for everyone

#104

Post by magicalhippo »

Retr0id wrote: post #89
spirodonfl wrote: post #48

I just tried. Asked a question on a research topic I'm digging into. It gave me some answers but no references. Then I copy the answers it gave me and specifically ask for references. Then I got: I sincerely apologize for my earlier response. Upon reviewing the search results provided, I realize I made an error in referencing those specific studies. The search results don't contain any relevant information for the cl…

> As an AI assistant, I should be more careful I hate this kind of thing so much.

I've been playing with Gemma locally, and I've had some success by telling it to answer "I don't know" if it doesn't know the answer, or similar escape hatches.

Feels like they were trained with a gun to their heads. If I don't tell it it doesn't have to answer it'll generate nonsense in a confident voice.

Re: Phind-405B and faster, high quality AI answers for everyone

#105

Post by mdp2021 »

Retr0id wrote: post #89
spirodonfl wrote: post #48

I just tried. Asked a question on a research topic I'm digging into. It gave me some answers but no references. Then I copy the answers it gave me and specifically ask for references. Then I got: I sincerely apologize for my earlier response. Upon reviewing the search results provided, I realize I made an error in referencing those specific studies. The search results don't contain any relevant information for the cl…

> As an AI assistant, I should be more careful I hate this kind of thing so much.

Absolutely. Behaviour that in normal life in clean societies would be "eliciting violence": automated hypocritical lying, apologizing in form and not in substance, making statements based on fictional value instead of truthfulness...

Re: Phind-405B and faster, high quality AI answers for everyone

#106

Post by caskstrength »

josvdwest wrote: post #68

"A key issue with AI-powered search is that it is just too slow compared to classic Google. Even if it generates a better answer, the added latency is discouraging." Is this true? I feel like most complaints I have and hear about is how inaccurate some of the AI results are. I.e. the mistakes it confidently makes when helping you code.

This is true in my experience. Before searching for something I often try to guess whether it will take me more time to quickly go over Google results or watch Perplexity Pro slowly spitting the answer line-by-line.

Re: Phind-405B and faster, high quality AI answers for everyone

#107

Post by caskstrength »

dsp_person wrote: post #17

Hmm this versus Kagi Assistant? Plan page says $20/mo Unlimited powerful Phind-405B and Phind-70B searches; Daily GPT-4o (500+) , Claude 3.5 Sonnet (500+), Claude Opus (10) uses > Phind-405B scores 92% on HumanEval (0-shot), matching Claude 3.5 Sonnet. Any other benchmarks?

Yeah, just went over their pricing and they apparently don't have any lower tier subscription besides 20$/month "unlimited Phind + 500/day ChatGPT" version. I don't need that, what I need is something like 100 uses per month for 5$. As a coding-focused search engine they really need to consider why would people pay them same rates as for more feature-rich competitors.

Re: Phind-405B and faster, high quality AI answers for everyone

#108

Post by moffkalast »

josvdwest wrote: post #68

"A key issue with AI-powered search is that it is just too slow compared to classic Google. Even if it generates a better answer, the added latency is discouraging." Is this true? I feel like most complaints I have and hear about is how inaccurate some of the AI results are. I.e. the mistakes it confidently makes when helping you code.

It's one of those triangles with speed \ accuracy / cost.

You can have a small model that's cost effective to serve, and gives fast responses, but will be wrong half the time.

Or you can have a large model that's slow to run on cheap hardware, but will give more accurate answers. This is usually only fast enough for personal use.

And the third option with a large model that's fast and accurate, and you'll have to pay Nvidia/Groq/etc. a small fortune to be able to run it at speed and also probably build a solar powerplant to make it cost effective in power use.

Re: Phind-405B and faster, high quality AI answers for everyone

#109

Post by ithkuil »

magicalhippo wrote: post #104
Retr0id wrote: post #89

Earlier quoted context omitted.

> As an AI assistant, I should be more careful I hate this kind of thing so much.

I've been playing with Gemma locally, and I've had some success by telling it to answer "I don't know" if it doesn't know the answer, or similar escape hatches. Feels like they were trained with a gun to their heads. If I don't tell it it doesn't have to answer it'll generate nonsense in a confident voice.

The models weights are tuned towards the direction that would cause the model to best fit the training set.

It turns out that this process makes it useful at producing mostly sensible predictions (generate output) for text that is not present in the training set (generalization).

The reason that works is because there are a lot of patterns and redundancy in the stuff that we feed to the models and the stuff that we ask the models so there is a good chance that interpolating between words and higher level semantics relationship between sentences will make sense quite often.

However that doesn't work all the time. And when it doesn't, current models have no way to tell they "don't know".

The whole point was to let them generalize beyond the training set and interpolate in order to make decent guesses.

There is a lot of research in making models actually reason.

Re: Phind-405B and faster, high quality AI answers for everyone

#110

Post by shultays »

navaed01 wrote: post #85
jadbox wrote: post #54

Earlier quoted context omitted.

In my tests, it does hallucinate answers, even with Phind 70B. For example, I asked for bluetooth earplugs that have easy battery replacements. It always kept giving me answers for earplugs with I know have their battery soldered into the casing. Tbf, perplexity also fails at this question.

‘Easy battery replacements’ is pretty subjective. This feels like one of those error that demonstrate how good the tech is, because it’s being used for very specific and subjective requests

It should be able to figure out what an average joe would understand from such questions. I think any human would interpret "easy battery replacement" as "you can just remove the old battery out and put the new one in". If a random person asked you such a question, would you assume he has the tools and the skill needed to solder new batteries and considers that easy?
Post reply on HN