Kolibri is Aleph Alpha's open-weight German and English LLM: 78B parameters, 3.5B per token. How it works, what it's good and bad at, and when to use it.
19 comments
Lucasoato14 minutes ago
> 4. It thinks in German
This means that it’s always on time, it uses acronyms for everything and when there’s a decision to be made, it sets up a committee.
hypfer10 minutes ago
Do we get the same kind of jokes with other nationalities too?
9dev35 minutes ago
Aleph Alpha is just a sad joke by now. The talent isn't there anymore, they never managed to catch up to the other labs, failed to deliver on several projects, and by now are just a cash grab for the investors.
gchamonlive13 minutes ago
Only if you think in terms of short term gains, but thinking in the long run, doesn't really matter if these models are crap today, all models will eventually be obsolete, unless we plateau hard on every aspect of the tech.
What matters is to have good sovereign models in 5, 10, 20 years time.
roncesvalles6 minutes ago
I'm curious why you think sovereign models matter that much if open source ones exist (unless that stops at some point). Sovereign model hosting services, yes.
d2kx22 minutes ago
German here. We are cheering for Mistral, which is making some good moves before the year is over, and Black Forest Labs for non-coding. But that's about it.
hypfer9 minutes ago
Speak for yourself and yourself only.
driverdan19 minutes ago
IMO the announcement is better https://aleph-alpha.com/en/blog/kolibri-has-landed-a-soverei...
sajithdilshanabout 1 hour ago
> It knows less from memory, Multi-turn tool calling is weaker, It’s not the best coding agent
Then what does it good at? Sending faxes?
mhitza44 minutes ago
I don't have the hardware to test this, but being trained to say "I don't know" instead of misleadingly talking confidently about what it does not know is interesting in itself.
skrebbelabout 1 hour ago
Well that’s a pretty important skill for German users!
sajithdilshan22 minutes ago
Unfortunately yes.
m00dy20 minutes ago
I was thinking about the use cases for Germany residents actually, but yes, you're right. A German AI model needs to be able to handle fax machines (there's a bit variety of them) and also needs to handle letters coming home. german image-to-text.
stogotabout 1 hour ago
GPT was better at chat and rag before coding
Read the full thread on Hacker News →
Related stories
- The Verge · 0 points · 5 days ago
- Can you forget how you feel about Meta?theverge.comThe Verge · 0 points · 11 days ago
- The Verge · 0 points · 7 days ago
- Can John Ternus find Apple’s next big thing?theverge.comThe Verge · 0 points · 12 days ago
- Hacker News · 73 points · 11 days ago
- The Verge · 0 points · 2 days ago