April 2026

What does it say about crypto market structure when the exchange that invented the perpetual swap decides its own institutional clients would rather not keep assets on the exchange at all? That is the question raised by Zodia Custody’s latest integration, which brings BitMEX live on Interchange, Zodia’s off-venue settlement network. The setup lets Zodia Custody Limited (UK) clients trade directly on BitMEX while their assets stay in segregated cold storage, moving only at the point of settlement. […]

Ver mais

Three pieces in this series covered how open source trust infrastructure gets degraded from outside: by corporate extraction, government neglect, and funding failures. This one is about what happens when AI enters that same stressed infrastructure, and what the community is building in response. This is the fourth piece in a series on open source sustainability and security infrastructure. The first covered the HashiCorp licensing controversy and what it revealed about the open source social contract. The second […]

Ver mais

Heterophily is a prevalent property of real-world graphs and is well known to impair the performance of homophilic Graph Neural Networks (GNNs). Prior work has attempted to adapt GNNs to heterophilic graphs through non-local neighbor extension or architecture refinement. However, the fundamental reasons behind misclassifications remain poorly understood. In this work, we take a novel perspective by examining recurring inductive subgraphs, empirically and theoretically showing that they act as spurious shortcuts that mislead GNNs and reinforce non-causal correlations […]

Ver mais

I am teaching a robot how to “solve” a maze using DQN. For weeks now it has been converging to possibly the worst policy it possibly could which is to drive backwards into a wall no matter what and accrue enormous negative rewards. I have modulated an enormous amount of variables, hyper-parameters, changed neural network size, drastically altered reward structure in various ways, tried different state inputs, tons of initial exploration, given it memory, made the optimal policy […]

Ver mais

Particle accelerator beamline optimization is a high-dimensional control problem traditionally requiring significant expert intervention. We present RLABC (Reinforcement Learning for Accelerator Beamline Control), an open-source Python framework that automatically transforms standard Elegant beamline configurations into reinforcement learning environments. RLABC integrates with the widely-used Elegant beam dynamics simulation code via SDDS-based interfaces, enabling researchers to apply modern RL algorithms to beamline optimization with minimal RL-specific development. The main contribution is a general methodology for formulating beamline tuning as a […]

Ver mais

The gap between fast-moving AI agents and slow traditional capital formation is no longer sustainable. Founders can now build and scale agentic ventures at unprecedented speed, yet raising capital, structuring governance, and aligning incentives still drag projects down with delays, misaligned tokens, and outdated models. Fresh off research into onchain capital formation and decision markets, Olayimika Oyebanji sat down with Umia co-founder Francesco Mosterts to discuss why today’s tokens are broken, how continuous market-driven governance can fix it, […]

Ver mais

I spent years calling models via API : Bedrock, Sagemaker, Anthropic. This week was about understanding what’s actually happening inside the box, and why that matters for building systems around it. Coming into this project, I had built production AI systems on AWS Bedrock using flows, agents. I knew how to wire models into applications. What I didn’t know was what the models were actually doing with the text I gave them, why RAG works at all, or […]

Ver mais

What 10 years of trust-based platforms and one zero-to-one product unlocked about intent qualification along with the mechanism most marketing and growth teams are missing. I’ve spent over a decade working inside trust-based technology platforms. Consumer products where a stranger getting into your car, opening their home to you, or meeting you alone in a foreign city were the entire value proposition. Platforms which operated across 20+ markets or even across several continents, with millions of users. In […]

Ver mais

There was a time when the internet felt obviously human. It was messy in a human way. Slow humanly. Personal in a human way. People wrote bad blog posts with too much passion and not enough editing. Forums ran on obsession. Websites looked strange because someone made them, not because a design system told them to. Search results felt like trails left behind by actual people. Even the chaos had fingerprints on it. That version of the internet […]

Ver mais