March 2026

We consider robustness against data corruption in offline multi-agent reinforcement learning from human feedback (MARLHF) under a strong-contamination model: given a dataset $D$ of trajectory-preference tuples (each preference being an $n$-dimensional binary label vector representing each of the $n$ agents’ preferences), an $ε$-fraction of the samples may be arbitrarily corrupted. We model the problem using the framework of linear Markov games. First, under a uniform coverage assumption – where every policy of interest is sufficiently represented in the […]

Ver mais

Banking house JPMorgan Chase is asking its roughly 65,000 engineers and technologists to use AI tools as part of their regular workflow. Business Insider reported that managers are tracking how often staff use these tools. That use may also influence performance reviews. The report states employees are encouraged to use tools like ChatGPT and Claude Code when writing code, reviewing documents, or handling routine tasks. Internal systems then classify workers based on their level of use. Some are […]

Ver mais

:::info Authors: Yuanzhi Li, Microsoft Research S´ebastien Bubeck, Microsoft Research Ronen Eldan, Microsoft Research Allie Del Giorno, Microsoft Research Suriya Gunasekar, Microsoft Research Yin Tat Lee, Microsoft Research ::: Abstract We continue the investigation into the power of smaller Transformer-based language models as initiated by TinyStories – a 10 million parameter model that can produce coherent English – and the follow-up work on phi-1, a 1.3 billion parameter model with Python coding performance close to the state-of-the-art. The […]

Ver mais

Guiding collective motion in biological groups is a fundamental challenge in understanding social interaction rules and developing automated systems for animal management. In this study, we propose a deep reinforcement learning (RL) framework for the closed-loop guidance of fish schools using virtual agents. These agents are controlled by policies trained via Proximal Policy Optimization (PPO) in simulation and deployed in physical experiments with rummy-nose tetras (Petitella bleheri), enabling real-time interaction between artificial agents and live individuals. To cope […]

Ver mais

AI-powered code review tools have become a staple in modern engineering. They automate repetitive checks, accelerate delivery, and maintain consistency across pull requests. For smaller teams or contained projects, this alone can drive meaningful gains in efficiency and output. But as organizations scale, the dynamic changes. Software is no longer a single, self-contained codebase; it’s an ecosystem of interconnected services, shared APIs, and constantly evolving dependencies. In these environments, reliability isn’t determined by how clean a pull request […]

Ver mais

Every SaaS IT director knows the drill. Engineering is rushing a release to hit a revenue goal, a dozen new sales reps are demanding CRM access yesterday, and then a critical vulnerability notification lands in your inbox. Speed usually wins when the pressure is on, so you grant admin rights to unblock a developer or pause a fleet-wide update to keep a sales demo running smooth. These all feel like tactical necessities in the moment, but they create […]

Ver mais

:::info Astounding Stories of Super-Science October 2022, by Astounding Stories is part of HackerNoon’s Book Blog Post series. You can jump to any chapter in this book here. THE MURDER OF ROGER ACKROYD – THE PARAGRAPH IN THE PAPER Astounding Stories of Super-Science October 2022: THE MURDER OF ROGER ACKROYD – THE PARAGRAPH IN THE PAPER By Agatha Christie ::: Caroline, of course, had not failed to see Miss Russell come to the surgery door. I had anticipated this, […]

Ver mais