Wits and scribbles
Some thoughts, almost worth reading.Sententia
Conjectures and refutations
The limits of my prompt
February 2026Post status: incomplete thinking, workshopping timeboxed writing. In plain words: What technical interviews might look like in a few years. Writing style: Weird math formalism interspersed w...
Tokens for nothing and your (cognitive) chips for free
May 2025Post status: ad-hoc reaction to X post. In plain words: Thinking before doing looks like cheating. Writing style: GPT-curated blockquotes, then marginalia on Krakauer.
Marginalia
Demanded post-scriptum.
- Conformal Classification of Neural NetworksOct 2021
- Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd SchemaOct 2021
- Probing Emergent Semantics in Predictive Agents via Question AnsweringOct 2021
- KG-based world modelsOct 2021
- Simple Few-Shot Learning with Language ModelsJul 2021
- Learning to communicate about shared procedural abstractionsJun 2021
- Reward is enoughJun 2021
- Making Sense of Sensory Input; Apperception codeJun 2021
- Are Convolutional NNs or Transformers more like Human Vision?May 2021
- Flexible modulation of sequence generation in the entorhinal–hippocampal systemMay 2021
- 26 more →
Symposia
Compelled a record.
- Learning salon: Kimberly StachenfeldAug 2021
- Learning salon: Jane WangAug 2021
- Learning Salon: Recap & DiscussionJun 2021
- Learning salon: Zenna TavaresMay 2021
- Ideas about a new programming language for gamesMay 2021
- Learning Salon: Simon KornblithApr 2021
- Learning Salon: Blake RichardsFeb 2021
- Learning Salon: Katja Hofmann, Deep RL for GamesFeb 2021
- Learning Salon: Recap and Panel DiscussionFeb 2021