61.
63.
Nvidia says it can shrink LLM memory 20x without changing model weights
(venturebeat.com)
65.
66.
67.
Prompt-caching – auto-injects Anthropic cache breakpoints (90% token savings)
(news.ycombinator.com)
68.
Ceno, browse the web without internet access
(news.ycombinator.com)
69.
What we learned from a 22-Day storage bug (and how we fixed it)
(news.ycombinator.com)
70.
Understanding the Go Runtime: The Scheduler
(news.ycombinator.com)
71.
Bcachefs creator insists his custom LLM is female and 'fully conscious'
(news.ycombinator.com)
72.
75.
Running AI models is turning into a memory game
(techcrunch.com)
78.
How DSQL makes sure sequences scale
(news.ycombinator.com)
79.
Expensively Quadratic: The LLM Agent Cost Curve
(news.ycombinator.com)
80.
81.
82.
Show HN: HN Companion – web app that enhances the experience of reading HN
(news.ycombinator.com)
83.
Nintendo 3DS emulation is getting a big performance boost
(androidauthority.com)
84.
Three Cache Layers Between Select and Disk
(news.ycombinator.com)
86.
87.
How to Scale a System from 0 to 10M+ Users
(news.ycombinator.com)
88.
89.
Today's top topics:
openai
nintendo
apple
sony
google
chatgpt
shinyhunters
apple watch
switch 2
android authority