digitado

About digitado

https://www.digitado.com.br

Posts by :

Here's how F1 is tweaking its hybrid systems to try to save the show

Here’s how F1 is tweaking its hybrid systems to try to save the show

⋅

After spending the last couple of weeks discussing the problem, Formula 1’s stakeholders have arrived at a number of solutions to the sport’s hybrid energy problem. F1 started this year with all-new powertrains with much more powerful electric motors than ever before, but with batteries that can only send full power to those motors for a few seconds a lap. Once exhausted, the power halves until there’s more charge in the battery. In qualifying this ruins the show, […]

Ver mais

Liked Liked
llm-openrouter 0.6

llm-openrouter 0.6

⋅

Release: llm-openrouter 0.6 llm openrouter refresh command for refreshing the list of available models without waiting for the cache to expire. I added this feature so I could try Kimi 2.6 on OpenRouter as soon as it became available there. Here’s its pelican – this time as an HTML page because Kimi chose to include an HTML and JavaScript UI to control the animation. Transcript here. Tags: openrouter, llm, llm-release, pelican-riding-a-bicycle, kimi, ai-in-china, llms, ai, generative-ai

Ver mais

Liked Liked

Bounded Ratio Reinforcement Learning

⋅

Proximal Policy Optimization (PPO) has become the predominant algorithm for on-policy reinforcement learning due to its scalability and empirical robustness across domains. However, there is a significant disconnect between the underlying foundations of trust region methods and the heuristic clipped objective used in PPO. In this paper, we bridge this gap by introducing the Bounded Ratio Reinforcement Learning (BRRL) framework. We formulate a novel regularized and constrained policy optimization problem and derive its analytical optimal solution. We prove […]

Ver mais

Liked Liked

Bounded Ratio Reinforcement Learning

⋅

Proximal Policy Optimization (PPO) has become the predominant algorithm for on-policy reinforcement learning due to its scalability and empirical robustness across domains. However, there is a significant disconnect between the underlying foundations of trust region methods and the heuristic clipped objective used in PPO. In this paper, we bridge this gap by introducing the Bounded Ratio Reinforcement Learning (BRRL) framework. We formulate a novel regularized and constrained policy optimization problem and derive its analytical optimal solution. We prove […]

Ver mais

Liked Liked

When Can LLMs Learn to Reason with Weak Supervision?

⋅

Large language models have achieved significant reasoning improvements through reinforcement learning with verifiable rewards (RLVR). Yet as model capabilities grow, constructing high-quality reward signals becomes increasingly difficult, making it essential to understand when RLVR can succeed under weaker forms of supervision. We conduct a systematic empirical study across diverse model families and reasoning domains under three weak supervision settings: scarce data, noisy rewards, and self-supervised proxy rewards. We find that generalization is governed by training reward saturation dynamics: […]

Ver mais

Liked Liked
Robot runner handily beats humans in half-marathon, setting new record

Robot runner handily beats humans in half-marathon, setting new record

⋅

Humanoid robots outran the fastest human competitors while surpassing the human world record during a half-marathon event held in Beijing on April 19. The demonstration of fast-improving robotic speed and autonomy comes as China’s tech industry is rapidly scaling up mass production of humanoid robots to explore possible uses in the real world. The fastest robot from Chinese smartphone-maker Honor notched a winning time of 50 minutes and 26 seconds while autonomously navigating the 13-mile (21-kilometer) route, according […]

Ver mais

Liked Liked
Deezer says 44% of new music uploads are AI-generated, most streams are fraudulent

Deezer says 44% of new music uploads are AI-generated, most streams are fraudulent

⋅

Music streaming services like Spotify and YouTube Music have become the primary way people listen to music, which can be a lot more convenient than buying individual albums. However, this also makes it easier for AI-created tracks to worm their way into your playlists. Most streamers don’t go out of their way to label AI music, but Deezer has worked to develop technology to identify that content. In a recent update, the company says AI music is approaching […]

Ver mais

Liked Liked
ToolSimulator: scalable tool testing for AI agents

ToolSimulator: scalable tool testing for AI agents

⋅

You can use ToolSimulator, an LLM-powered tool simulation framework within Strands Evals, to thoroughly and safely test AI agents that rely on external tools, at scale. Instead of risking live API calls that expose personally identifiable information (PII), trigger unintended actions, or settling for static mocks that break with multi-turn workflows, you can use ToolSimulator’s large language model (LLM)-powered simulations to validate your agents. Available today as part of the Strands Evals Software Development Kit (SDK), ToolSimulator helps you […]

Ver mais

Liked Liked
Rogue Trooper brings the Genetic Infantry to the silver screen

Rogue Trooper brings the Genetic Infantry to the silver screen

⋅

For more than 49 years, a comic called 2000 AD has been responsible for giving science-fiction junkies a weekly infusion of “thrill power.” Published in the UK, far from the action in Hollywood, its characters have crossed over from the page to the screen far less frequently than the superheroes belonging to Marvel and DC. Judge Dredd has two movies of varying quality, but attempts to follow the 2012 version with a TV show appear to have sputtered […]

Ver mais

Liked Liked

Learning the Riccati solution operator for time-varying LQR via Deep Operator Networks

⋅

We propose a computational framework for replacing the repeated numerical solution of differential Riccati equations in finite-horizon Linear Quadratic Regulator (LQR) problems by a learned operator surrogate. Instead of solving a nonlinear matrix-valued differential equation for each new system instance, we construct offline an approximation of the associated solution operator mapping time-dependent system parameters to the Riccati trajectory. The resulting model enables fast online evaluation of approximate optimal feedbacks across a wide class of systems, thereby shifting the […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2026