The secret is finally out! 🍌🚀
I’ve been testing Gemini Nano Banana 2.1 for quite some time now as part of the Gemini API Early Access Program, and it is officially live today!
I am honestly so impressed by this model.
Its biggest strengths: 🧠 Built-in "thinking" & reasoning capabilities 🖼️ Native image generation (all the way up to crisp 4K!) ⚡ Incredible speed/latency at a super developer-friendly price point
Huge congrats to the teams at @GoogleAIDevs and @GoogleAIStudio on this launch!
Peak tok/s is a vanity metric. If your serving stack violates TTFT & TPOT SLOs, production goodput is near zero.
I broke down how to benchmark vLLM fairly on @OpenXLA /TPUs vs CUDA, covering interconnects, compilation costs, & MBU:
youtu.be/-AjLjr5kPqY?si=JJns…
@GoogleDevsNA
I built ConferenceRank: 980+ CORE-ranked venues, 300+ live AoE deadlines with 1-click calendar sync, acceptance rates, and an AI abstract-to-venue suggester. Free, no login 🚀
rabimba.github.io/Conference…
The video for my DevLab 2026 talk is finally out! 🎬
If you couldn't make it live, here is the full breakdown of "The Throughput Trap." We look past mirage-like public benchmarks to explore real-world LLM serving.
📺 Watch: youtu.be/-AjLjr5kPqY📝
Tired of tracking CS conference deadlines and doing AoE timezone math at 2 AM?
I built ConferenceRank: 980+ CORE venues, 300+ live AoE countdowns, 1-click Cal sync, acceptance rate stats, and an AI venue suggester.
Free & zero-login:
rabimba.github.io/Conference…
From “What can I get you?” to “I know exactly what you’ll like.” ☕🤖
Today at #RenderATL 2026, I’m leading a hands-on lab on building a Coffee Recommendation Agent with Google ADK + RAG.
📍 BLD ATL, Floor 3 – Expo Hall
⏰ 11:30 AM ET
Presenting our paper on passive prompt injection in LLM-based SOC log analysis at @USENIXSecurity on Aug 12! 🛡️
A collab by @PayPal AI Labs, @UHouston & @KentState. Catch our poster too! In the area? Let's meet up!
📄 arxiv.org/abs/2607.14493
🔗 usenix.org/conference/usenix…
Excited to speak at @Google's Dev Lab Summer 2026 (invited by the Google ML & PyTorch teams)!
"Benchmarking vLLM on XLA Backends: From CUDA to OpenXLA for LLM Serving"
@JeffDean also has a talk! Come say hi!
rsvp.withgoogle.com/events/d…
@GoogleDevsNA @googledevs @PayPal
"How good is this driver, right now, this lap?"
If your AI coach doesn't answer that, it's guessing. In Part 2 of my Racecraft series, I explain how we use input jerk and coasting ratios to build a continuous, skill-adaptive DriverModel. 🏎️
rkrants.blogspot.com/2026/06…
If an AI coach gives you feedback 800ms late, it’s worse than silence. At 130 km/h, a late cue is a safety hazard. 🏎️
I’m breaking down the 5-part technical series behind "Racecraft", my on-device, real-time AI coach built on Gemma 4.
rkrants.blogspot.com/2026/06…
"How good is this driver, right now, this lap?"
If your AI coach doesn't answer that, it's guessing. In Part 2 of my Racecraft series, I explain how we use input jerk and coasting ratios to build a continuous, skill-adaptive DriverModel. 🏎️
rkrants.blogspot.com/2026/06…
Are your AI benchmarks just giving you a false sense of security?
As models scale, they hit "phase transitions" where your metrics break. If you're relying on static tests, you're just measuring how fast you're running toward a cliff.
rkrants.blogspot.com/2026/06…
My friend's MRI came on a CD we couldn't open, filled with 500+ cryptic images.
I built Dr.MRI.AI to fix that. An AI-powered, privacy-first tool using #Gemma4 to turn DICOM data into clear, clickable reports.
Read the story: rkrants.blogspot.com/2026/05…
Cooked something keeping my parents at mind today at @Stanford with @fastshot_ai
Check it out
youtube.com/shorts/NCY3MoYHu…
I’ve already been under the hood with #Gemma4 E2B!
1️⃣ A Multimodal Document Intelligence Pipeline (OCR + Agentic Tools)
2️⃣ The Fine-tuning Cookbook (QLoRA & rsLoRA)
Check it out:
🔗 rkrants.blogspot.com/2026/04…
🔗 rkrants.blogspot.com/2026/04…
@GoogleDeepMind @GoogleDevsNA
Ever wished you could see dense academic papers? 🤯 Google just announced Nano Banana 2 (Gemini 3.1 Flash Image)! It brings insane speed, 4K fidelity & precise subject control to visualize complex science.
Check out my early access deep dive: rkrants.blogspot.com/2026/02… #AI #Gemini
Something I helped built for @Google is live now :)
I unfortunately wasn't able to attend the field test day due to @UH_NSM awarding me uh.edu/nsm/news-events/stori… on the same time.
But I am incredibly proud of what we all built for @googledevs as @GoogleDevExpert.
Deploy verifiable, physics-grounded AI with <15ms latency. 🏎️
A team of GDEs used a "split-brain" architecture to build a real-time racing coach in just two weeks. It combines Gemini Nano reflexes with Gemini 3.0 strategy to eliminate hallucinations.
Learn more → goo.gle/3Z2llwT
ALT A group of ten smiling individuals pose around a silver BMW race car on a paved track under an overcast sky. The car features a BMW logo on its grille, custom hood vents, yellow headlights, a red tow hook, and a small "B" sticker on its front bumper; a person in the foreground wears a black sweatshirt with a prominent glittery number "3". In the background, a white race car with "38X" and "NASA" text is visible, alongside large support vehicles and tall wind turbines.
Rabimba Karanjai @[email protected] retweeted
I was there as promised ✍️🇳🇬
The future of Blockchain with Life AI will be 100X of scalability
@LifeNetwork_AI @rabimba , @EntropianDeFi , @tuan_lifeai
