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

General Developer Forum In The News
, ,
1

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.

1 Like
2

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:

1 Like
3

Will have to check it out… keep us posted Tom!

4

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

1 Like
5

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:

1 Like