Open Source

31180 readers

140 users here now

All about open source! Feel free to ask questions, and share news, and interesting stuff!

Useful Links

Rules

Posts must be relevant to the open source ideology
No NSFW content
No hate speech, bigotry, etc

Related Communities

Community icon from opensource.org, but we are not affiliated with them.

founded 5 years ago

MODERATORS

[email protected]

123

Open-source ChatGPT Alternative (jan.ai)

submitted 8 months ago by [email protected] to c/[email protected]

46 comments fedilink hide all child comments

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

[–] [email protected] 7 points 8 months ago (3 children)

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

[–] [email protected] 4 points 8 months ago (3 children)

Would you say it's noob-friendly?

[–] [email protected] 4 points 7 months ago

Yes

[–] [email protected] 3 points 7 months ago

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

[–] [email protected] 1 points 7 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.

[–] [email protected] 3 points 7 months ago (1 children)

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

[–] [email protected] 2 points 7 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.

[–] [email protected] 3 points 8 months ago (3 children)

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.

[–] [email protected] 2 points 7 months ago

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

[–] [email protected] 2 points 7 months ago (1 children)

Train it online. Use it offline.

[–] [email protected] 1 points 7 months ago (1 children)

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.

[–] [email protected] 2 points 7 months ago (1 children)

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.

[–] [email protected] 3 points 7 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.

[–] [email protected] 1 points 7 months ago

I use Stealth or Starling, usually.