
Neural networks do math by rotating shapes. We found a shape-rotating calculator hidden inside an LLM โ and itโs used for more than just math! (1/6)
๐ธ๐ฆ๐๐๐ค ๐๐๐ฅ๐๐๐๐๐๐๐ฅ๐๐ค
6K posts

@AulasInteligent
Inteligencia Artificial aplicada en todo tipo de entornos. Dos docentes diferentes con un mismo destino: Juan Luis & Guillermo. Opina el de en medio.

Neural networks do math by rotating shapes. We found a shape-rotating calculator hidden inside an LLM โ and itโs used for more than just math! (1/6)


You've been asking for this one... Now in preview: Codex in the ChatGPT mobile app. Start new work, review outputs, steer execution, and approve next steps, all from the ChatGPT mobile app. Codex will keep running on your laptop, Mac mini, or devbox.




I'm disappointed I have to even point it out. There is no cohesion to the depth and color choices. The reflection of the tree bleeds into the lilypads with no regard for spatial depth or contrast. The background lilypad-algae amalgam is egregiously vague, like most AI art.











My first paper is now on arXiv: Instrumental Choices. We ask a simple question: when an LLM agent can finish a real task by following the rules or by taking a useful policy-violating shortcut, which path does it choose?





