-
The technical name for this is the Prompt API (official spec, Chrome docs). It's been in Chrome's bowels since version 138 — initially behind a flag, now also available as an Origin Trial for production sites. The big news is that a critical mass of developers just figured out it's there, and the demos hitting HN every week (Decaf rewriting comments, Subtitle Insights translating YouTube live, the side-panel UI above) are no longer "look what's possible" — they're "I shipped it last weekend."
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
Rapid-MLX
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
💡 💡 Make the fallback cheap to operate. The whole point of using Nano on the supported path is reduced cost. If your fallback is GPT-5.5 at $5/M tokens, you've moved the bill, not deleted it. Two patterns work well: (1) route the fallback to a smaller hosted model (Haiku, Gemini Flash, Mistral Small) that matches Nano's "short summarization" sweet spot; (2) for Mac users specifically, run Rapid-MLX as your /api/llm endpoint — Apple Silicon owners get on-device performance via your server's Mac, not theirs. Same thesis as our DeepClaude guide: the harness is one product, the model is another, and you can swap them.
-
⚠️ ⚠️ Mozilla's pushback isn't just standards politics. Per The Register's coverage, Mozilla's formal opposition is that the Prompt API "encourages model-specific behavior that harms interoperability" — early-2000s browser-sniffing, but for LLM quirks. If you only target Chrome, you'll write prompts that work great on Nano and silently break on whatever Apple ships next. The fallback in Step 4 isn't only for unsupported browsers; it's also your hedge against being locked into Nano's prompt style.
Related posts
-
"A benchmark for catching when code doesn't do what its documentation claims"
-
I tried to break my own MCP prompt-injection detector. One class of attack walks straight through - and it isn't a bug.
-
Show HN: PyTorch on Java
-
Playing with Vision Embeddings
-
The Smallest Brain You Can Build: A Perceptron in Python