bookshelf | mason wang

Takeaways and comments from my readings, from ML research to fiction.

Where do you know what you know? The representation of semantic knowledge in the human brain 8 8 17m +2 +1 Functional Alignment Can Mislead: Examining Model Stitching | arXiv ----15m +3 +2 +1 Multi-user Speech BCI with Rapid New-User Adaptation | bioRxiv ------ +4 +3 +2 Revisiting the Platonic Representation Hypothesis: An Aristotelian View | arXiv ----20m +1 (vec2vec) Harnessing the Universal Geometry of Embeddings | arXiv ----53m +2 +1 A Martian Sends a Postcard Home | Craig Raine 7 ---- +3 +2 +1 A Small, Good Thing | Raymond Carver 8 --39m +3 +2 +1 Inner…

saved by

• Trevor Trinh
• KRUPAL VIRANI

related reading

• Readmezhengdongwang.com
• Jean-Rémi KINGkingjr.github.io
• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• A global workspace in language models \ Anthropicanthropic.com
• Representation of the world in the human brainyoutube.com
• Semantic reconstruction of continuous language from non-invasive brain recordings | Nature Neurosciencenature.com
• https://io0.github.ioio0.github.io
• Why I’m leaving OpenAI to build telepathynaomibashkansky.com
• High-level visual representations in the human brain are aligned with large language models | Nature Machine Intelligencenature.com
• The Platonic Representation Hypothesisphillipi.github.io
• AI to Interpret Your Mindjonathanxu.com
• Alephalephneuro.com