logoalt Hacker News

elorantyesterday at 7:41 PM2 repliesview on HN

Wow, this is fucking phenomenal. I fed it a long transcript asking it to create a summary and it executed it extremely well. For an 8B model this is quite impressive.


Replies

SubiculumCodeyesterday at 8:25 PM

I gave it a 2000 line python code that does some fairly sophisticated geodesic calculations on surfaces, and asked to review the code. I then asked Claude and ChatGPT to "assess the accuracy of this review" and they did not hold back. That said, its a very small model, and very fast.

ValdikSStoday at 8:58 AM

Bad at translation, at least to Russian. Very fast though, about 2x faster than Gemma 4 e2b on my CPU.