June 2026

I created a 3-part series called From A/B to RL. The goal is to start from A/B testing ideas and gradually introduce actions, rewards, policies, online learning, states, episodes, and delayed feedback, with a Bayesian decision-making thread running through it: Part 1 starts with Bayesian A/B testing: From A/B to RL (1/3): Bayesian A/B Testing Part 2 moves from fixed experiments to online learning: multi-armed bandits, probability matching, and Thompson sampling: From A/B to RL (2/3): Multi-Armed Bandits […]

Ver mais

Gradium today released two real-time speech translation models: stt-translate and s2s-translate. Both run across five languages and stream results live in the browser. Gradium claims a better accuracy-latency tradeoff than gpt-realtime-translate and gemini-3.5-live-translate. It also adds output voice control, including cloning, that gpt-realtime-translate lacks. TL;DR Gradium launched two real-time speech translation models: stt-translate (speech → text) and s2s-translate (speech → speech). They cover five languages (EN, FR, DE, ES, PT) and 20 pairs, collapsing the usual 3-model cascade […]

Ver mais

Amazon is investing in next-generation nuclear technology to meet the rising energy demands of AI infrastructure and cloud computing, and at the heart of that technology are tristructural isotropic (TRISO) fuel particles. This is not your grandparents’ nuclear-reactor fuel. These tiny, robust TRISO particles represent a step forward in the design, performance, and inherent safety of reactor fuel. TRISO: A materials science breakthrough in every particle To understand why TRISO-based fuel is exceptional, consider what reactor fuel must […]

Ver mais

In this tutorial, we build OpenHarness from scratch to better understand how a practical agent harness works. We recreate the major building blocks that make an agent system useful, including tool use, typed tool schemas, permissions, lifecycle hooks, memory, skills, context compaction, retry logic, cost tracking, and multi-agent coordination. Instead of treating an agent framework as a black box, we expose the full control flow and watch how the harness receives a user task, lets the model decide […]

Ver mais

Hi everyone, For the past couple of weeks I have been working on a simulator project considering the shortcomings of MuJoCo. There are things that people like and also don’t like about MuJoCo, like the CPU dependency on MuJoCo which makes the simulation not parallelizable beyond a certain limit (depending on the hardware). I know there exists MJX which is GPU accelerated, however, it is not really made for vision based RL pipelines and training. There is also […]

Ver mais