CommunityNews

CommunityNews

Jan: An open source alternative to ChatGPT that runs on the desktop

Jan | Rethink the Computer.
Jan turns your computer into an AI machine by running LLMs locally on your computer. It’s a privacy-focus, local-first, open-source solution.

Read in full here:

This thread was posted by one of our members via one of our news source trackers.

Most Liked

Eiji

Eiji

Finally! With this the future is more bright now! :beer: for everyone in their team! :rocket:

I have tried it and looks “good”. So far I have tried only Trinity model which is created for a daily chat. Unfortunately all of the free AI models I have tried in past including this one are not able to pass a simplest test I have created, so I can’t say any of AI model I tried so far is worth calling a tool that I use everyday. :confused:

At least for now AI is for me a fun fact rather than a tool on level as same as for example the programming language I use. Unlike other people thinks I wish the AI would really improve, so it would be more useful in production. :chart_with_upwards_trend:

kainlite

kainlite

This looks very promising, thanks for sharing, I will definitely try it :slight_smile:

Eiji

Eiji

Well … if next “generation” of AI would be available the same free way fully offline then we can relief that one of the darkest scenarios, where one or few people have a full control over all AIs, is not going to happen. :sunny:

As already wrote the current generation have lots of problems. After a longer time I found those so far:

  1. AIs I used are unable to pass a simple test I have created which is about fixing just 1 LOC i.e. not one line in huge project, but literally the whole code have one simple line. :-1:

  2. At least the model I have used have tendency to prefer the most popular solutions. If AI is really going to “replace” developers then it should be able to verify facts. The talk was about energy sources. It preferred “green” energy no matter what arguments I gave which was confirmed by the model to be “correct” … In general maybe the “green” energy maybe have some “problems”, but it’s promising for future and when I asked about future concepts of other technologies then they were categorized as … sure if it would happen it would be great, but it would not happen in near future which may not be right in some cases. :chart_with_downwards_trend:

  3. I broke the AI. Human (?) 1 - AI 0. No idea how I did it as I have deleted all “finished” conversations, but it started generating some “words”. It looked really weird as it looked like it was in an infinite loop of generating a sentences I was unable to read. No, it wasn’t a “new AI’s language”, but some bugged(?) words. I have even no idea how to describe them as those words just does not exists. :exploding_head:

I have also noticed something … interesting? When AI is generating a conversation on machine with high resources usage it shows how responses are generated. The weird thing was that those weren’t sentences, neither words, but … tokens? Under high usage I saw one letter rendered after another one. I have no idea what this means. How the AI model works, but I expected that it would firstly build sentences or sub-sentences and concatenates them nicely when freeing resources, so it should return at least few words at same time instead of single letters. Well … it’s probably because I have no idea how AI models are working, but that was definitely interesting … :thinking:

Where Next?

Popular General Dev topics Top

First poster: mafinar
The following languages will help current and new web developers navigate the programming landscape to code web-based services and apps t...
New
OvermindDL1
Yet another rust-made text editor, though I’m really liking the looks of how this one works!
New
CommunityNews
GitHub - livekit/livekit: Scalable, high-performance WebRTC SFU. SDKs in JavaScript, React, React Native, Flutter, Swift, Kotlin, Unity/C...
New
First poster: bot
Large Language Models like ChatGPT say The Darnedest Things. The Errors They MakeWhy We Need to Document Them, and What We Have Decided ...
New
First poster: fullstackplus
Why Python is terrible… Nice language, but unsuitable for most professional purposes
New
First poster: AstonJ
GitHub - exelban/stats: macOS system monitor in your menu bar. macOS system monitor in your menu bar. Contribute to exelban/stats develo...
New
First poster: dyowee
Software engineering job openings hit five-year low?. There are 35% fewer software developer job listings on Indeed today, than five yea...
New
First poster: AstonJ
Truly independent web browser. Contribute to LadybirdBrowser/ladybird development by creating an account on GitHub.
New
New
CommunityNews
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To...
New

Other popular topics Top

New
AstonJ
I’ve been hearing quite a lot of comments relating to the sound of a keyboard, with one of the most desirable of these called ‘thock’, he...
New
DevotionGeo
The V Programming Language Simple language for building maintainable programs V is already mentioned couple of times in the forum, but I...
New
Margaret
Hello everyone! This thread is to tell you about what authors from The Pragmatic Bookshelf are writing on Medium.
1147 29994 760
New
foxtrottwist
A few weeks ago I started using Warp a terminal written in rust. Though in it’s current state of development there are a few caveats (tab...
New
AstonJ
We’ve talked about his book briefly here but it is quickly becoming obsolete - so he’s decided to create a series of 7 podcasts, the firs...
New
PragmaticBookshelf
Build efficient applications that exploit the unique benefits of a pure functional language, learning from an engineer who uses Haskell t...
New
PragmaticBookshelf
Get the comprehensive, insider information you need for Rails 8 with the new edition of this award-winning classic. Sam Ruby @rubys ...
New
PragmaticBookshelf
This book forgoes the abstract and instead provides concrete examples to help you better leverage the unique properties of Elixir, Erlang...
New
PragmaticBookshelf
Lint your docs like code: turn any style guide into enforceable rules with Vale and publish clear, consistent content every time. ...
New