Nash 🥇💙
14.7K posts
@neevash
Building @visionagents_ai • @GoogleDevExpert Dart & Flutter • @FlutterComm 💙 • Formula 1 fanatic 🏎 • Striving for excellence 💫
Anytime I've built something in Code *without* running it through the gstack pipeline, I've had to come back and rework it. Code is great but it also charges off half-cocked, solving whatever problem it thinks it sees, before asking if that's the *right* problem. gstack pushes you to take the time up front to ask "what am I actually trying to accomplish, what's the 10x version of that and what'll bite me later if I don't think about it now?" 10-15 minutes that saves hours of rework. Classic measure twice, cut once. And thank you again, @garrytan!
Holy shit. Now everyone will be able to use their @OpenClaws and all the other agentic platforms to build apps on top of X. Here's the secret: build lists. Lists are how you build apps. The pattern: Build a list of your favorite football team. Or whatever you are into. Then ask your AI agents "build an app showing me all the important news about my favorite football team." In minutes you'll have an app. And that's just the beginning. Your agent can build a script about your favorite football team that you can take to places like Google's Notebook LM. Now you have a video, a podcast, a slide deck, a game, a mind map. All about your favorite football team based on real time news. You can do the same with something like @HeyGen, create an avatar of your favorite football player. Now you will have your favorite football player telling you everything that's happening on the football team. And I could go for hours about how many things you can build and not even cover a fraction of them. This is huge. Thank you @elonmusk for making it possible to make millions of agentic apps affordably on top of X. Start building!
Dylan Sprouse held a trespasser at gunpoint before tackling him and pinning him to the ground until police arrived at his Hollywood Hills home. Wife Barbara Palvin, who was home at the time, called 911 reporting the attempted burglary. The suspect was arrested on existing warrants.
We push Prefill/Decode disaggregation beyond a single cluster: cross-datacenter + heterogeneous hardware, unlocking the potential for significantly lower cost per token. This was previously blocked by KV cache transfer overhead. The key enabler is our hybrid model (Kimi Linear), which reduces KV cache size and makes cross-DC PD practical. Validated on a 20x scaled-up Kimi Linear model: ✅ 1.54× throughput ✅ 64% ↓ P90 TTFT → Directly translating into lower token cost. More in Prefill-as-a-Service: arxiv.org/html/2604.1503…
We did it! We built the fastest interactive avatar model Introducing LemonSlice-2.1 𝘍𝘭𝘢𝘴𝘩 ⚡ Here’s how we did it using @modal and @livekit 👇 (note: it was not easy)
