isn’t Apple using it for its on-device typo/language correction Transformer? I remember when someone dumped the vocabulary it looked like they used modifier tokens.
@jeremyphoward
-
Exploring Repetition Tokens in AI Model Implementation
By
–
Oh I didn't know that – very cool. I wonder if they're using our repetition tokens too.
-
Claudette now supports async functionality
By
–
Even more good news on Claudette (
@AnthropicAI Claude's good friend!) — it now supports async too 😀 https://
claudette.answer.ai/#async -
LLM Integration with FastHTML Apps on Replit Platform
By
–
A *lot* of folks are asking how to get LLM help with FastHTML apps. @mattyp has provided a really nice walkthru showing how to set up @Replit to use FastHTML's LLM-ready context docs.
-
FastHTML Builds Web Apps in 24 Lines of Code
By
–
FastHTML does it in 24 lines of string concatenation
-
FastHTML Auto-rendering with __ft__ Method
By
–
If you rename “render” to “__ft__” then fasthtml will call it automatically, so you can just return the component from your handler directly!
-
ULMFiT technique adoption opportunity for major AI labs
By
–
We’ve been teaching this since 2017 and used it in ULMFiT, but still seems no big lab has picked up on it. Big opportunity for someone here…
-
Documentation Claims Lower Latency But Real Performance Differs
By
–
Yeah actually I’ve noticed that too – the docs claim lower latency, but I’m not seeing it
-
FastHTML Auto-render Components with __ft__ Method
By
–
If you rename “render” to “__ft__” then fasthtml will call it automatically, so you can just return the component from your handler directly!
-
FastHTML Framework Size Comparison with FastAPI
By
–
I believe that FastHTML is far smaller than FastAPI. It’s definitely not a big framework.