Mastodon posts mislabeled with the wrong language as well as costly translations that depend on a server: Those are common problems for many Mastodon instances. In this talk, Thomas Steiner from Chrome's Built-in AI team details how he integrated the Language Detector and Translator APIs into the popular Mastodon client Elk.zone. This isn't a textbook success story—you'll hear about what initially went wrong, the technical hurdles encountered, and how they were overcome to build a feature that now runs reliably in production.
Resources:
add support for the Language Detector API →
add support for the Translation API→
Elk Zone→
Chrome built-in AI docs →
Join the early preview program →
See more Web AI talks →
Subscribe to Chrome for Developers →
Event: Web AI Summit 2025
Speaker: Thomas Steiner
Products Mentioned: AI for the web
#ChromeforDevelopers #WebAI
|
Accelerators are getting faster, but is ...
For more details on this topic, visit th...
model that works best for your needs and...
With everything starting to use AI, ther...
Celebrate 10 years of Keras! 🎉 In this s...
Are you exploring JAX for the first time...
For more details on this topic, visit th...
Learn how Chrome handles permission upda...
CSS Selector Cheat Sheet: []( Web Dev Ro...
Building a recipe app? Stop worrying abo...
In this Python FastAPI tutorial, we'll b...
🔥AI-Powered Digital Marketing Certificat...
For only $1, you can claim a 1GB Residen...
WithSecure transformed threat analysis b...
Learn the fundamentals of creating APIs ...