Rabimba Karanjai @rabimba@toot.cafe (@rabimba) / X

8,850 posts

@rabimba

Working on #WebVR. ex-@mozilla . Opinions are my own. Googe Developer Expert - Web. Connect with me at @[email protected]

Houston, TX

Joined February 2009

Rabimba Karanjai @[email protected]
@rabimba
Jun 23
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/dev-lab… @GoogleDevsNA @googledevs @PayPal
Rabimba Karanjai @[email protected]
@rabimba
Jun 15
"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/teachi…
Rabimba Karanjai @[email protected]
@rabimba
Jun 15
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/racecr…
Rabimba Karanjai @[email protected]
@rabimba
Jun 9
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/the-bl…
Rabimba Karanjai @[email protected]
@rabimba
Jun 9
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/my-par…