Imagine every pixel on your screen, streamed live directly from a model. No HTML, no layout engine, no code. Just exactly what you want to see.
@eddiejiao_obj, @drewocarr and I built a prototype to see how this could actually work, and set out to make it real. We're calling it Flipbook. (1/5)
You're in an ML Engineer interview at Perplexity, and the interviewer asks:
"Your LLM generates millions of responses daily. How do you evaluate quality without manual review?"
Here's how you answer:
You're in an ML Engineer interview at Perplexity, and the interviewer asks:
"Your LLM generates millions of responses daily. How do you evaluate quality without manual review?"
Here's how you answer:
🚀 Follow-up to our last breakthrough on DeepSeek V3/R1 inference!
On NVIDIA GB200 NVL72, SGLang now achieves 26k input tokens/s and 13k output tokens/s per GPU with FP8 attention + NVFP4 MoE - that’s a 3.8× / 4.8× speedup vs H100 settings.
See the details in the 🧵 (1/4)
Perp DEXes, volume vs OI. Big spread here, most obvious regressor is pre-TGE vs post-TGE.
To compare with CEXes: Binance is 92%, OKX 80%, Bybit 184% according to @coinglass_com.
My response to AI 2027:
https://t.co/hqqXLM5UZl
The AI 2027 post is high quality, I encourage people to read it at https://t.co/84O5mfN5dh
I argue a misaligned AI will not be able to win nearly as easily as the AI 2027 scenario assumes, because it greatly underrates our ability to protect ourselves, especially given the (pretty magical) technologies that the authors admit will be available in 2029 in their scenario.
#UWAllen@UW & @nvidia researchers earned a #MLSys2025 Best Paper Award for boosting #LLM performance with FlashInfer—and showed “what’s possible when academia, industry & the open-source community innovate together,” says @ye_combinator. #AI#UWdiscovers https://t.co/cSxQXBJPpu
We've had so much fun organizing a vibe coding event for kids aged 9 to 13
that we decided to show our friends how to host one too
and turn it into a global event.
📆 It’s happening on October 10-11, 2025
🧑🏫 with in-person sessions hosted locally,
🌐 all connected in one giant global Zoom call
Imagine kids from around the world playing, discovering, learning, and hacking together using the latest AI vibe-coding tools from the amazing teams at Lovable and Rosebud AI.
If you're excited to be a local host, anywhere in the world, please sign up here 👉 https://t.co/OnfgW4zyr7
Full details on the wiki: https://t.co/llJYXO2qka
Discord: https://t.co/ZnJ86HXCyV