Jason Mayes
where else to find them
what they talk about
all 6 in the filters
where they keep going back
- Google I/O2 editions2021–2022
- JSNation2 editions2021–2024
all 8 in the filters
on a stage with
- Jarred Uttonce
- Jecelyn Yeenonce
- Jim Bankoskionce
all 6 in the filters
who talks about the same things
- Sandeep Gupta10 talks
- Shivay Lamba99 talks
- Kenji Baheux4 talks
- Charlie Gerard35 talks
- Nico Martin16 talks
- Laurent Picard14 talks
| title | conference | date |
|---|---|---|
| Client side Web AI Agents Building smarter user experiences for a future age | Build Stuff 2025 | 2025-12-03 |
Prototype demonstrates a browser agent that parses voice, extracts structured JSON, and calls existing page functions as tools to book flights and change… | ||
| State of client side AI | Web AI Summit 2025 | 2025-10-17 |
Claims that web AI runs entirely locally on consumer GPUs (demo on a 5‑generation‑old Nvidia 1070) and that Web AI usage grew from 1M to 1.2B yearly downloads… | ||
| Discover Web AI: Client side Agents, Gen AI, and machine learning in the browser | Web AI Summit 2025 | 2025-10-17 |
Demonstrates that full AI stacks run in-browser with Hugging Face collaboration and a Visual Blocks low-code pipeline built in seconds, claiming privacy, lower… | ||
| State of client side machine learning | Web AI Summit 2025 | 2025-10-17 |
Overview points and hard numbers: Google reports over 1 billion cumulative downloads of MediaPipe and TensorFlow.js with ~600 million downloads per year… | ||
| Client side Web AI Agents: Building smarter user experiences for future agentic ... | CityJS Athens 2025 | 2025-05-28 |
Prototype runs entirely client side using 2 billion parameter Gemma via the Mediap web LLM library, executing on a five‑generation GPU (Nvidia 1070 GPU) with… | ||
| Day 1 13 Jason Mayes | CityJS Athens 2025 | 2025-05-28 |
Demonstration builds an on-device agent that runs the Gemma 2B model in the browser via the Mediap web LLM library, exposes existing site functions as callable… | ||
| AI – Using AI During Development, What’s the Future of Development Going to Be, etc. | JSNation 2024 | 2024-06-13 |
-- no description -- | ||
| Web Apps of the Future With Web AI | JSNation 2024 | 2024-06-13 |
Argument that web AI runs real models in the browser with concrete wins: models run on-device via JavaScript, WebGPU and WebAssembly, TensorFlow.js and… | ||
| Transfer learning in JavaScript with TensorFlow.js | Google I/O 2022 | 2022-05-11 |
Builds a browser Teachable Machine clone that uses TensorFlow.js and a MobileNet v3 feature vector from TF Hub, resizing webcam frames to 224×224 and… | ||
| TensorFlow.js: From prototype to production, what's new in 2022? | Google I/O 2022 | 2022-05-11 |
TensorFlow.js adds concrete production-ready features: Coral Edge TPU support via tfjs-tflite-node for Node.js, a new selfie depth model for per-pixel… | ||
| Incredible things your community is creating with TensorFlow.js | Google's Machine Learning Virtual Community Day 2021 | 2021-11-09 |
YogaAI classifies six poses and runs a 10-second hold timer that pauses when detection fails; PoseNet extracts body keypoints and extrudes pose data into 3D/AR… | ||
| TensorFlow.JS 101: ML in the Browser and Beyond | JSNation Live 2021 | 2021-06-09 |
JavaScript with TensorFlow.js allows for machine learning in various environments, enabling the creation of applications like augmented reality and sentiment… | ||
| Machine learning for next gen web apps with TensorFlow.js | Google I/O 2021 | 2021-05-18 |
Library updates and concrete wins: 3.2M NPM downloads with ~50M CDN hits and 12.5k GitHub dependents; Face Mesh adds iris tracking; new pose models MoveNet (17… | ||
| Machine Learning on the web with TensorFlow.js | Google I/O 2021 | 2021-05-18 |
A live AMA that explains what TensorFlow.js actually does and how it is used: runs models in-browser and on Node.js, converts Keras/TensorFlow and TF Lite… | ||
| TensorFlow.js: Make a smart webcam in JS with a pre-trained ML model | Google I/O 2021 | 2021-05-18 |
Step‑by‑step live coding builds a working smart webcam using TensorFlow.js and the pre‑trained COCO‑SSD model that detects about 80 object classes in real… | ||
| Superpowers for next gen web apps: Machine learning | Chrome Dev Summit 2020 | 2020-12-09 |
Shows how TensorFlow.js runs full ML in the browser: use COCO-SSD for 90-object detection, Face Mesh 468 landmarks (3 MB) for real‑time face tracking at ~22–35… | ||
| TensorFlow.js 101: ML in the Browser and Beyond | ML Conf EU 2020 | 2020-11-05 |
TensorFlow.js runs full ML in-browser and on Node with concrete results: COCO‑SSD (90 classes) does real‑time webcam detection, FaceMesh is a 3 MB model with… | ||
| nothing matches | ||