Product blog
Product blog
Product updates, field guides, and field notes—each with links to docs and the hub where relevant. High-level milestones also appear on the changelog.
Topic
ReadField guide · Jun 12, 2026
Are AI photo editors safe? What to check before you upload
Where your photo actually goes in an AI editor, how to read the privacy policy, the on-device alternative, and a quick checklist before uploading anything personal.
- Where your photo goes
- Reading a privacy policy
- A pre-upload checklist
NSS Background Remover
ReadField guide · Jun 12, 2026
Model quantization: how big AI models shrink to run in a browser
A plain-English explanation of the technique that makes on-device AI possible: why a model’s size is the gatekeeper for running it in a browser, what a model actually is under the hood, how quantization stores its numbers in fewer bits for a roughly four-times reduction, why models tolerate the lost precision, what it costs in accuracy, and how it combines with distillation and pruning.
- A model is billions of numbers
- Fewer bits ≈ 4× smaller
- Tiny accuracy cost, huge size win
NSS Background Remover
ReadField guide · Jun 8, 2026
What on-device AI can't do yet
The honest edges of in-browser AI: frontier models, heavy video, tight memory, and when a fallback wins.
- Frontier models stay cloud-bound
- Phone memory has a ceiling
- Sometimes a fallback wins
NSS Background Remover
ReadField guide · Jun 7, 2026
Why on-device AI is private by design
The difference between “we promise not to look” and “the data physically cannot leave.”
- Structural, not policy
- No upload, no log
- The model comes to you
NSS Background Remover
ReadField guide · Jun 7, 2026
What runs on your device vs in the cloud
A practical guide to telling on-device AI from cloud AI, and what each implies.
- On-device: many tasks
- Cloud: huge models
- How to tell
NSS Background Remover
ReadField guide · Jun 7, 2026
How AI runs in your browser (WebGPU and WebAssembly, explained)
A plain-language explainer of the browser tech that makes on-device AI fast enough to use.
- WebGPU uses your GPU
- WASM is the fallback
- No install needed
NSS Background Remover
ReadField guide · Jun 7, 2026
The privacy cost of free AI tools
What "free" can really mean when your images or audio are uploaded to a server.
- Uploads = exposure
- Read the terms
- Free + private is possible
NSS Background Remover
ReadField guide · Jun 7, 2026
Do browser AI tools work offline?
How on-device AI tools keep working without a connection, and what still needs the network.
- Works after first load
- PWA + cached model
- No connection needed
NSS Background Remover
ReadField guide · Jun 6, 2026
How big are in-browser AI models (and why size matters)
Why an on-device model is tens to hundreds of megabytes — and why that download is worth it.
- ~80 MB Fast, ~180 MB Best
- Downloads once, then cached
- Size is the price of privacy
NSS Background Remover
ReadField guide · May 30, 2026
Bring your own ONNX model: running your own weights in the browser
The logical end state of on-device AI — if the computation happens on your machine, the model does not have to be ours. How BYO-ONNX works and why it exists.
- Host your own ONNX at a URL
- WebGPU primary, WASM fallback
- Seven swappable capabilities
NSS Background Remover