TurboQuant: Redefining AI efficiency with extreme compression
(news.ycombinator.com)
1.
2.
3.
5.
Nvidia says it can shrink LLM memory 20x without changing model weights
(venturebeat.com)
8.
Prompt-caching – auto-injects Anthropic cache breakpoints (90% token savings)
(news.ycombinator.com)
9.
Ceno, browse the web without internet access
(news.ycombinator.com)
10.
Understanding the Go Runtime: The Scheduler
(news.ycombinator.com)
11.
Bcachefs creator insists his custom LLM is female and 'fully conscious'
(news.ycombinator.com)
12.
15.
Running AI models is turning into a memory game
(techcrunch.com)
18.
How DSQL makes sure sequences scale
(news.ycombinator.com)
19.
Expensively Quadratic: The LLM Agent Cost Curve
(news.ycombinator.com)
20.
21.
Show HN: HN Companion – web app that enhances the experience of reading HN
(news.ycombinator.com)
22.
Nintendo 3DS emulation is getting a big performance boost
(androidauthority.com)
23.
Three Cache Layers Between Select and Disk
(news.ycombinator.com)
25.
26.
How to Scale a System from 0 to 10M+ Users
(news.ycombinator.com)
27.
28.
29.
30.
AMD Ryzen 7 9850X3D review: The world's fastest gaming processor, again
(tomshardware.com)
Today's top topics:
meta
google
openai
amazon
child safety
new mexico
daredevil
android
social media
samsung