126

Open-source ChatGPT Alternative (jan.ai)

submitted 6 months ago by yogthos@lemmy.ml to c/opensource@lemmy.ml

53 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[-] JackGreenEarth@lemm.ee 7 points 6 months ago

I've been using Jan for a while now. It's great!

[-] Churbleyimyam@lemm.ee 4 points 6 months ago

Would you say it's noob-friendly?

[-] JackGreenEarth@lemm.ee 4 points 6 months ago

Yes

[-] priapus@sh.itjust.works 3 points 6 months ago

It's extremely noob friendly. You really don't need any prior knowledge to start using this.

[-] Kindness@lemmy.ml 1 points 6 months ago

Very. Just have a good enough internet connection and hardware to download and run models. Interrupted downloads must start over. 4-41 GB. Otherwise find the source, use wget, and download to the correct folder.

[-] nutbutter@discuss.tchncs.de 3 points 6 months ago

Is it better than GPT4All? Do they provide their own model(s) or do we have to download it from other sources?

[-] JackGreenEarth@lemm.ee 2 points 6 months ago

The provide a hub of models, in my case it was better than gpt4all because it didn't crash, but I also think it has a nicer user interface.

[-] Showroom7561@lemmy.ca 3 points 6 months ago

Is there a model you prefer? I've been throwing the exact same question to different models and they seem to all give a very similar answer.

Also, how is it getting certain information if it's all offline? For example, I asked it to recommend some bike products, and gave very specific brands and models.

[-] silas@programming.dev 2 points 6 months ago

Trinity stood out the most to me, it seems to have less unnecessary fluff

[-] joeldebruijn@lemmy.ml 2 points 6 months ago

Train it online. Use it offline.

[-] Showroom7561@lemmy.ca 1 points 6 months ago

That's crazy impressive, though. I've been playing with it more, and it's very specific about certain things. I guess you can hold a lot of data in the GB of space these models use.

[-] joeldebruijn@lemmy.ml 2 points 6 months ago

Agree, no small feat. Two caveats tho:

These models prioritize plausibility above factual correctness. So verification often is needed.
Data from after the creation of trainingmaterial is absent of course.

[-] Showroom7561@lemmy.ca 3 points 6 months ago

These models prioritize plausibility above factual correctness. So verification often is needed.

100% I was telling my wife that anyone who knows about a subject, can easily point out the inaccuracies with the output from any of the models.

But if you don't know about a subject, the AI gives you an answer that seems like it could be right. Scary to see where this technology takes us, especially when the majority easily digests information without verifying any of it.