[HN Gopher] Jan: An open source alternative to ChatGPT that runs...
       ___________________________________________________________________
        
       Jan: An open source alternative to ChatGPT that runs on the desktop
        
       Author : billybuckwheat
       Score  : 95 points
       Date   : 2024-03-21 18:56 UTC (4 hours ago)
        
 (HTM) web link (jan.ai)
 (TXT) w3m dump (jan.ai)
        
       | ShamelessC wrote:
       | Quite a lot of polish and bragging about stars and tweets for an
       | open source project. Is there hidden monetization of some sort?
       | Perhaps VC funding?
        
         | anewhnaccount2 wrote:
         | According to their page https://jan.ai/team/ they aim to
         | bootstrap.
        
           | ShamelessC wrote:
           | Awesome thanks.
        
       | afian wrote:
       | Fantastic product and excellent team!
        
       | thedangler wrote:
       | I don't see anything about it reading local documents like exel,
       | pdfs, or docs. Anyone see how this is accomplished?
        
         | 0134340 wrote:
         | Is it implied anywhere? That's a feature I'd love and also why
         | I haven't bothered delving into LLMs very much; I didn't know
         | there were any that could locally index your library and train
         | on that data. I'd love to ask it a question and have it
         | reference my local ebook library.
        
       | throwitaway1123 wrote:
       | This looks interesting. I would love a comparison between this
       | product and LM Studio.
        
       | ThrowawayTestr wrote:
       | Where does the model come from?
        
         | LordDragonfang wrote:
         | Afaict, it doesn't have any inbuilt model, you just download
         | one yourself or hook up to someone's API.
        
         | dsp_person wrote:
         | Scroll down on the main page:
         | 
         | 01 Run local AI or connect to remote APIs
         | 
         | 02 Browse and download models
        
       | thesurlydev wrote:
       | These kinds of apps are becoming dime a dozen. It would be nice
       | to know how this one differentiates itself. Not obvious from the
       | website.
        
         | viraptor wrote:
         | It seems like that until you actually try to use them. Not many
         | are actually polished, support formatting, history, and
         | multiple endpoints. There's lots of trivial apps abandoned
         | after a few days, but what are the actually functional, good
         | quality alternatives to this one? (That don't pass your
         | query/answer through a third-party for data collection)
        
           | extr wrote:
           | I use https://www.typingmind.com/. It is paid, but I've found
           | it to be a reliable front end to OpenAI/Claude/Google,
           | supporting everything you mention. I haven't done any hyper
           | detailed security audit but after watching network requests
           | I'm pretty confident it's not sending my chats anywhere
           | except to the relevant provider endpoints.
           | 
           | Considering how much I use it, I've found it to be well worth
           | the cost. The creator is pretty on top of model/API changes.
        
             | karmajunkie wrote:
             | i'll second that recommendation... i use it through the
             | SetApp store and i've been very pleasantly surprised by its
             | documentation and ability to work with most services.
        
             | viraptor wrote:
             | It's not a standalone app though. There's lots of web
             | interfaces, but that's not the same. (I mean, it's a cool
             | thing, but not what jan.ai is)
        
       | moose44 wrote:
       | Running LLMs locally always feels so awesome!
        
       | pryelluw wrote:
       | Would be nice if they listed system requirements. Their docs just
       | say coming soon ...
        
         | knodi123 wrote:
         | most of their docs say coming soon. and their whole wiki.
         | 
         | honestly feels like site this was launched a couple of days too
         | soon.
        
           | warkdarrior wrote:
           | Their LLM is still generating copy for the website..
        
       | christkv wrote:
       | I got say I've been using LLM studio as it exposes the models in
       | the ui as well as through a local open ai compatible server so I
       | can test different models against my workflows locally.
        
       | TheRealPomax wrote:
       | Still hoping we'll eventually stop using Fibonacci to show off
       | recursion, because that's one of those examples where the _maths_
       | might be expressed as recursive relation, but the
       | _implementation_ should never be =)
       | 
       | Good AI would go "you don't want that, that's horribly
       | inefficient. Here's an actually performant implementation based
       | on the closed-form expression".
        
         | zopa wrote:
         | Nah, good AI would run in the compiler and optimize the
         | recursion into something fast.
        
       | pimlottc wrote:
       | I'm going to assume this is not an Australian company...
       | 
       | https://www.youtube.com/watch?v=2akt3P8ltLM
        
         | badRNG wrote:
         | Looks like they are based out of Singapore
        
       | LeoPanthera wrote:
       | Is this a fork of "LM Studio"? The UI is suspiciously similar,
       | even down to the layout of the labels.
        
       | onion2k wrote:
       | I use Jan to run Mistral locally. It works well for what I need
       | (which amounts to playing with models).
        
       | FuriouslyAdrift wrote:
       | Many LLMs may be run locally with GPT4All...
       | 
       | https://gpt4all.io/
        
       | LeoPanthera wrote:
       | Unless I just can't find it, there seems to be no setting for
       | customizing the prompt format for local models. You can edit the
       | prompt itself, but not the format of the prompt or the subsequent
       | messages. This would make using many models difficult, or give
       | poor results, since they don't all use the same format.
        
       | kkfx wrote:
       | I try some LLM on my notes and well... They was unable to give me
       | insights that are hard to spot, like follow the flaw of notes
       | identifying patterns, find similar notes from the past and so on.
       | In ALL cases classic tags/riprgrep full-text search was far
       | quicker and equally or more effective.
       | 
       | Long story short: LLMs might be useful on hyper big mass of
       | information, like a new kind of search engine that try do achieve
       | a semantic goal mimicking it. But not more than that IMVHO.
       | Marginally LLMs might help computer-illiterate to manage their
       | files, seen https://www.theverge.com/22684730/students-file-
       | folder-direc... but I doubt they can go any further for the next
       | 5+ years at least.
        
       | lagrange77 wrote:
       | I was wondering if it uses something like vLLM[0] or
       | Llama.cpp[1].
       | 
       | Seems to be Llama.cpp via 'Nitro', which was discussed here
       | before [2].
       | 
       | [0] https://github.com/vllm-project/vllm
       | 
       | [1] https://github.com/ggerganov/llama.cpp
       | 
       | [2] https://news.ycombinator.com/item?id=38887531
        
       ___________________________________________________________________
       (page generated 2024-03-21 23:01 UTC)