@benno_krojer
postdocing w @davidbau @Northeastern, prev @Mila_Quebec @AIatMeta @CisLmu. Interests: interp, multimodality, reasoning, cogsci. Fun: 🥨⚽🧩🏛️🥏📚
AI
One post says Dominik's result looked more convincing than expected; another praises novel ideas rather than just scaling.
AI
A post considers how logit lens and J-lens might work with character-level or multiword tokens, arguing that even simple interpretability tools depend on data and low-level design choices.
AI
A researcher urges junior researchers to hone their writing and think carefully about what individual words mean and evoke in readers.
