Researchers at MIT CSAIL demonstrate that frontier LLMs like GPT-6 Astra can natively read and write neural network weights without gradient descent, identifying trained behaviors from raw weights and writing …
An exploration of using GPT-OSS-120B to directly edit the weights of a trained LunarLander policy in response to physics changes, without gradient updates. The experiment successfully repaired reversed thrusters and …
Perpetual futures are no-expiration derivatives that use a periodic funding rate to keep prices anchored to spot, and have dominated crypto trading globally before receiving CFTC approval for U.S. markets. This paper …
A deep dive into the architecture and engineering principles behind always-on, persistent AI agents that can run autonomously for extended periods, covering context management, durable workflows, sub-agent orchestration, …
This paper introduces harness learning, a method that trains a proposer model to revise executable agent programs using execution feedback, framed as meta-learning over code. Experiments show the approach generalizes to …
TypeSafe AI introduces System One Models and Jev, a new class of frontier AI models optimized for fast, structured, type-safe decisions rather than text generation. Jev achieves comparable intelligence to existing LLMs …
This paper proposes tensor logic, a programming language that unifies neural and symbolic AI through tensor equations based on the equivalence between logical rules and Einstein summation. The language elegantly …
A pre-registered field experiment with 776 Procter & Gamble professionals found that individuals using AI matched the performance of two-person teams, broke down functional silos between R&D and Commercial roles, …
A comprehensive survey of machine learning applications in financial markets, covering return prediction models, risk-return factor models, stochastic discount factor estimation, and optimal portfolio construction. The …
A modern re-examination of the classic 1979 paper arguing against formal verification, exploring how AI coding agents and recent tooling advances have changed the landscape. The author revisits each historical objection …
