Blair Johnson

Our hypothesis: LLMs have a pressure for information density, leading to compressed language, novel ngrams, and a preference for short alternatives in linguistic alternations, even when this is not humanlike - humans have a pressure for successful communication with other humans

Most models these days are perfectly competent agents, and my daily frustration is that they are all completely inept communicators. Remember when labs were trying to solve Diplomacy? It feels like they've completely forgotten that there's a human on the other end that needs to understand sometimes.

o1-preview beat my family zero-shot at Codenames when paired with the weakest guesser. Clues weren’t amazing when picking word pairs for itself, but very impressive ability to relate words when given a collection and asked for a clue that relates them all.

jax.config.update(“jax_explain_cache_misses”, True) is an extremely useful tool for figuring out what parts of your Jax program are getting recompiled and why.

Had a great week at SC24! Very exciting to see the ways that diffusion and other ML algorithms are transforming scientific computing. The tooling community also seems to be making big strides to make HPC more accessible to a broader scientific community. Look forward to next year!