FutureSim Exposes Polymarket AI’s Narrow Wins and Failures
Max Planck Institute researchers recently released FutureSim, a benchmark for polymarket ai-style forecasting that tests whether agents can predict real-world…
-
-
10^7-Dimensional LLM Memory, but Only If it Stays Sparse
A BDH seminar summary circulating in recent technical discussion frames LLM memory as a tradeoff between the familiar transformer KV…
-
DeepSeek Forces Visual Reasoning Through Points and Boxes
DeepSeek has released an open-source visual reasoning framework called Thinking with Visual Primitives. According to 36Kr, the system changes how…
-
A Formula From Another Field Opened Erdős Problem
Erdős problem #1196 now has a serious claimed solution, and the evidence ladder is unusually visible. Liam Price posted GPT-5.4…
-
302 Designs, 16 Hits: AI-Designed Viruses in the Lab
AI-designed viruses are now a lab result, but not in the way the viral posts made it sound. Researchers affiliated…
-
A 14-Author Paper Tries to Make Deep Learning Theory a Science
A 14-author perspective paper posted to arXiv on April 23 argues that deep learning theory is starting to look less…
-
LLM Failure Modes Start in the Stack, Not the Chat
LLM failure modes are easiest to understand if you stop treating them as personality flaws, “the model lied,” “the chatbot…
-
66 Tokens Make a Diffusion Language Model Look Easy
A diffusion language model generates text by starting from masked or otherwise corrupted tokens and iteratively restoring them. In this…
-
Language-Agnostic Representations Show a Shared Semantic Workspace
The standard story is that LLMs work in words. They predict the next token, so surely their internal reasoning is…
