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

Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

phind.com

Post reply on HN
Print view View original

251–260 of 358 posts

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#251

Post by idonotknowwhy »

buildbot wrote: post #69

Well, neither GPT4 or this Phind model where able to answer my torture test: "Write amaranth code that can be used to control the readout of a frame from a kodak CCD with 4096 columns and 2048 rows." Which yes, is missing a lot of detail (you could/I have feed/fed in a datasheet). But Phind goes off on using pyserial (?!), and GPT4 assumes amaranth is a hypothetical CCD control library and makes a useless class contr…

I have no idea what that means (even after googling it) lol. This is how my local WizardLM-70B responded to your prompt.

https://pastebin.com/BCAthV8y

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#252

Post by slowhadoken »

pbhjpbhj wrote: post #148
lsaferite wrote: post #102

Earlier quoted context omitted.

Interestingly, I'd say that _not_ being able to give citations helps protect the LLM from copyright issues. That being said, I'm much prefer if the LLM could provide citations for every piece of information it was trained on and uses to provide an answer.

Citations are essential for me as I'm using Phind for work and can't rely on "trust me bro". It needs to confirm to my expectations or be confirmed in a couple of the citations that have trustworthy sources (eg are from known domains, well-cited journals, etc.).

I've found great sites and devs using Phind.

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#253

Post by idonotknowwhy »

zoogeny wrote: post #112

I just spent a few minutes doing a comparison between Phind and GPT-4 for a very high-level question on a distributed job queue. I gave them both the same fairly vague sketch of a kind of system I would like to build. Here are my impressions: In the positives of Phind: * Phind was able, even eager, to recommend specific libraries relevant to the implementation. The recommendations matched my own research. GPT-4 takes…

This is a good point about GPT-4, it can intuit the "question behind the question" really well compared with other models. And it's been profoundly useful for me with the most random tasks I knew nothing about prior (like fixing a wall in my house), etc.

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#254

Post by slowhadoken »

donmcronald wrote: post #234
Racing0461 wrote: post #29

Earlier quoted context omitted.

As a user, i perfer getting the right response compared to the thing spitting out a link. (not saying phind is bad). Lets focus on getting llm right before nerfing it in its baby stages.

Give me the citations every day of the week. The source of information matters. For example, I don't rely on any ZFS info or opinions I find online if I can't verify it came from a contributor or highly reputable person that has a lot of experience with ZFS. If you want to show the warts of all these LLMs, ask it about ZFS if you know enough to spot the commonly parroted misinformation that plagues the internet. IMHO…

Transparency is paramount. If OpenAI doesn't want to make it's proprietary software open to academic scrutiny I completely understand. However, if their app is going to play an educational role then sources and citation are mandatory in academic content.

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#256

Post by slowhadoken »

make3 wrote: post #39
slowhadoken wrote: post #9

I love that Phind cites what it scrapes. This should be the obligation of all LLM. I always suggest people use it over ChatGPT.

What they're citing isn't what the LLM "scraped", it's what the retrieval model fed to the LLM. You're not guaranteed that it's what it actually used to give you the output, and it's also definitely not all the text that it used to get appropriate knowledge to generate the answer, as this is split over whatever millions of examples for the language and for human language in a non human-understandable way

I've heard this coldtake before but OpenAI's source code isn't open to academic scrutiny. So I don't understand why some people are so confident about how it works. It's certainly not magic and Phind seems to be capable of it citation.

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#257

Post by elif »

Hmm I wonder what kind of code quality can be accomplished by looping from phind->gpt->copilot for multiple iterations, asking for criticisms of the code qualities then seeking code which addresses the ai-generated criticisms etc until it knocks out better than I would in a second.

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#258

Post by happycube »

seydor wrote: post #115
accrual wrote: post #56

> it supports up to 16k tokens > Llama 1 supports up to 2048 (2K) tokens, Llama 2 up to 4096 (4K), CodeLlama up to 16384 (16K). [0] This is wild to me. The token window is one of the limiting factors for having an AI that can actually remember you and past conversations. Having a large window is key for future AI applications that involve long running conversations (weeks, months, years). The tech is already very imp…

640k is enough for anyone

Extending that analogy, imagine what one could do with 128B tokens.

On cast off/cheap workstation/server hardware.

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#259

Post by ojosilva »

donmcronald wrote: post #237
rushingcreek wrote: post #233

Earlier quoted context omitted.

Phind Plus is $15/month and Phind Pro is $30/month. There is a 2x price difference, not an 8x difference. And Phind Pro comes with (virtually) unlimited GPT-4 uses. We understand that the incentives of setting daily limits for search aren't great, which is why the Phind model is unlimited for free. GPT-4, however, is unfortunately too expensive for us not to charge past a certain usage threshold.

Plus costs $0.016 per search and Pro costs $0.002 per search. https://www.phind.com/search?cache=wgyz13tg4jkbl9pklptmpds5

To me the $15/mo plan is just bait so users pick the target $30/mo month. Why would you pay $0.016/search when you can pay 8x less and feel smart about making that choice?

edit: looking at it again, I think the $15/mo is actually just for people who wants Phind "private", so that their data is not used for training.

Re: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

#260

Post by nick-sta »

donmcronald wrote: post #237
rushingcreek wrote: post #233

Earlier quoted context omitted.

Phind Plus is $15/month and Phind Pro is $30/month. There is a 2x price difference, not an 8x difference. And Phind Pro comes with (virtually) unlimited GPT-4 uses. We understand that the incentives of setting daily limits for search aren't great, which is why the Phind model is unlimited for free. GPT-4, however, is unfortunately too expensive for us not to charge past a certain usage threshold.

Plus costs $0.016 per search and Pro costs $0.002 per search. https://www.phind.com/search?cache=wgyz13tg4jkbl9pklptmpds5

Cost per search isn't really a great metric. For me, I hit the cap of 30 searches/day pretty easily, but 500 is pretty hard to hit. For me, its just a question of what tier matches my volume.
Post reply on HN