How OpenAI delivers low-latency voice AI at scale
(news.ycombinator.com)
1.
2.
3.
Show HN: What happens when you load a webpage (Interactive)
(news.ycombinator.com)
4.
5.
6.
7.
Queueing Requests Queues Your Capacity Problems, Too
(news.ycombinator.com)
8.
9.
Post-Quantum Web Could be Safer, Faster
(darkreading.com)
10.
11.
Bunny Database
(news.ycombinator.com)
12.
Stargaze: SpaceX's Space Situational Awareness System
(news.ycombinator.com)
13.
Nobody likes lag: How to make low-latency dev sandboxes
(news.ycombinator.com)
14.
Taming P99s in OpenFGA: How we built a self-tuning strategy planner
(news.ycombinator.com)
15.
Three types of LLM workloads and how to serve them
(news.ycombinator.com)
16.
Stop using natural language interfaces
(news.ycombinator.com)
17.
Razer’s new concept headphones have built-in cameras and all the AI you need
(androidauthority.com)
18.
The Curious Case of the Shallow Session SPAs
(news.ycombinator.com)
19.
20.
21.
22.
We replaced H.264 streaming with JPEG screenshots (and it worked better)
(news.ycombinator.com)
23.
25.
What Does a Database for SSDs Look Like?
(news.ycombinator.com)
27.
Golang optimizations for high‑volume services
(news.ycombinator.com)
28.
Evaluating Uniform Memory Access Mode on AMD's Turin
(news.ycombinator.com)
29.
I put a real search engine into a Lambda, so you only pay when you search
(news.ycombinator.com)
30.
Measuring Latency (2015)
(news.ycombinator.com)
Today's top topics:
openai
android authority
samsung
apple
intel
google
tsmc
android
microsoft
sam altman