AT Mot: introducing AT Mot, a small experiment to rebuild Wordle on AT Proto. Give it a try! This was mostly an excuse to play with Constellation, as @pevohr.bsky.social suggested a few days ago. Thank you! herve.bzh/at-mot-i-rebuilt-wordle-on-th…
AT Mot: I rebuilt Wordle on the AT Protocol
herve.bzhJun 24, 2026 at 11:48 PM
AT Mot: I rebuilt Wordle on the AT Protocol
Introducing AT Mot, a small ATProto experiment, and a daily word game. Give it a try!
I haven't made anything with AT Proto yet
This is the blog post I write before I actually build anything on AT Proto
AT Mot — a daily word game on atproto
Guess the daily 5-letter word in English or French. Built on the AT Protocol — your data is yours.
An AT Proto lexicon currently under consideration and development
An AT Proto lexicon currently under consideration and development · GitHub
typelex – An experimental TypeSpec syntax for Lexicon
An experimental TypeSpec syntax for AT Protocol Lexicons. Write Lexicons in a more readable syntax using TypeSpec.
Why Does ChatGPT "Delve" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models
Scientific English is currently undergoing rapid change, with words like "delve," "intricate," and "underscore" appearing far more frequently than just a few years ago. It is widely assumed that scientists' use of large language models (LLMs) is responsible for such trends. We develop a formal, transferable method to characterize these linguistic changes. Application of our method yields 21 focal words whose increased occurrence in scientific abstracts is likely the result of LLM usage. We then pose "the puzzle of lexical overrepresentation": WHY are such words overused by LLMs? We fail to find evidence that lexical overrepresentation is caused by model architecture, algorithm choices, or training data. To assess whether reinforcement learning from human feedback (RLHF) contributes to the overuse of focal words, we undertake comparative model testing and conduct an exploratory online study. While the model testing is consistent with RLHF playing a role, our experimental results suggest that participants may be reacting differently to "delve" than to other focal words. With LLMs quickly becoming a driver of global language change, investigating these potential sources of lexical overrepresentation is important. We note that while insights into the workings of LLMs are within reach, a lack of transparency surrounding model development remains an obstacle to such research.
AT Mot is a fun new daily word game built right on the AT Protocol. Guess the 5 letter word in 6 tries, with support for both English and French! @atmot.herve.bzh
AT Mot
atstore.fyiAtproto guides
Tutorials about at proto and how to use it
How It Works | Bluesky Protocol Services
pub search
On an Atmosphere OS - Scott's Thoughts
Why good non-techie user documentation is vital for a wider embrace of the ATmosphere - Debbie's Blatherings - by Debbie Ridpath Ohi
What It Means for Universities to Run Their Own PDS: The Potential of DID as Academic Infrastructure - Nightflight
i want to do a little ✨ ama about atproto ✨ in this thread. no question is too simple if you’ve been curious about atproto but don’t know…
