Sujee Maniyam

🐍 Snakes at the Nebius booth @ Nvidia GTC '26🐍 …not that kind of snakes 😄 It’s the classic Snake game - but each snake is controlled by an LLM in real time. Powered by Nebius Token Factory @nebiustf 📍 Last day of the conference 🎮 Try different models and watch them compete live Stop by the @nebiusai booth 👀 #Snakegame #LLMGames

Demoing Nebius Token Factory (@nebiustf ) to a "potential future customer" 🤖 at #nvidiagtc 😁 @UFBots @nebiusai

“Nebius will take care of you,” — Jensen Huang, @NVIDIA’s Founder and CEO, in conversation with our CRO Marc Boroditsky at the Nebius booth here at #NVIDIAGTC. We will.

Come checkout cool robots (powered by Nebius) from @UFBots at @nebiusai booth at #nvidiagtc

Nvidia $NVDA CEO Jensen Huang is in the Nebius $NBIS booth right now at GTC

Nebius.Build SF is coming to San Francisco on March 15 at Shack15. A one-day, in-person builder event for engineers working on inference and robotics systems. 150+ AI builders. Two technical tracks. One full day of building. What to expect: - Token Factory workshop: run and optimize open-source models - Robotics workshop: Cosmos-2 and GR00T VLA with real robots - Hack sprint from 1:30 - 8:00 PM with demos and awards - $25,000+ in prizes, including GTC passes This is for teams pushing on latency, throughput, cost, reliability and real-world autonomy. Fully in person. Space is limited. Teams of up to four. Apply here: cerebralvalley.ai/e/nebius-build…

1/8 Training draft models for speculative decoding almost always relies on KL divergence – a proxy, that typically leads to convergence to suboptimal solutions under limited capacity. We introduce LK losses: training objectives that directly target acceptance rate instead. We show consistent gains across 4 architectures and 6 target models (8B → 685B), up to 8-10% acceptance length, with zero added overhead. arxiv.org/abs/2602.23881 🧵

This is such a cool idea ! Let's do a similar style #pickleball 🏓 tournament in the US 👍

@nebiustf Watch dedicated end point scaling up to handle traffic youtube.com/watch?v=4RlTHx…

"control your AI infrastructure ... without the headache of managing it" 👉 @nebiustf dedicated end points : nebius.com/blog/posts/ded…

Great inference = powerful models + great infrastructure ⚡ If you’re curious about modern inference engineering, come learn about: 🔧 Model shaping: fine-tuning, distillation, speculative decoding ⚡️ Model serving at scale: Auto-scaling, KV cache, Cache-aware routing, Disaggregated prefill ...and how we are implementing these at @nebiustf. 📅 Feb 26 (Thu) ⏰ 9am PT / 12pm ET / 6pm CET Can’t make it live? Register - we’ll send the recording + notes. 👉 nebius.com/events/webinar…

@jxnlco @jxnlco, an avid Obsidian user here. I would love to know your workflow / integrations with Obsidian @obsid

Been going to work at 6am and leaving the office at 9:30pm. I’m not feeling the AGI but slack integrations with codex automations into my obsidian has basically allowed me to me to panopticon the every person and channel that’s public in company

Our Amsterdam HQ is officially open. We welcomed the local team for Day 1 this week. Now it’s time for our global team to experience their first day in our new space. Take a look inside our new home in Amsterdam. 👇 #LifeatNebius

The AgentBeats–AgentX Competition Phase 1 winners have been announced - and the projects are fantastic. Huge congratulations to all the teams involved! 👏 Read the highlights here: berkeleyrdi.substack.com/i/188179396/ag… Now, on to Phase 2 : rdi.berkeley.edu/agentx-agentbe…

(another car wash post) Q: I want to wash my car. The car wash is 50 meters away. Should I walk or drive? Kimi K2.5: (thought 52 secs) : Drive the 50 meters, but maybe take the long way around the block to let the engine warm up slightly ... GLM 4.7 (thought 42 secs): If your car has a manual transmission (stick shift) and the road is flat, you might choose to **push** the car to save fuel and avoid the wear of starting the engine just for a 50-meter drive ... (see image for full answer) sometimes the models do overthink :-)

1 - Is your agent doing the right thing? Is it making the correct tool calls? Learn how to monitor and debug your agents with @LangWatchAI. 2 - Want to use Claude Code with powerful open-source models like Kimi 2.5, GLM 4.7, or Qwen3-Coder? Join us for Nebius Builder Hour! (@nebiustf ) 🗓️ Feb 18. 9:00 PST / 12:00 EST / 18:00 CET 👉 nebius.com/events/webinar…