Interesting! And indeed very relevant as it enables control over the similarity modeled by the embeddings. Figure 2 is really cool. Which base embeddings were used for this?

Can you point to where "LLM knowledge" can be found in this graph?

Source: en.wikipedia.org/wiki/Knowledge

I think they hot-fixed the year though. Either answers correctly or refuses when I ask

Happy not Friday everyone

Proposing "kilometers cycled in 2 weeks" as a new success metric for research groups 🚴‍♀️📊🥇
@mainlp.bsky.social #stadtradeln

comes with a well-being feature prompting you to take writing breaks before major conferences! 🧘‍♂️

arcprize.org/arc-agi-pub