June 2026

For the last few years, AI has been sold as a machine for finding answers. Better answers, faster answers, answers hidden somewhere in mountains of data no person could realistically sort through on their own. To be fair, it has delivered some of that. Teams can summarize meetings almost instantly. Managers can get a snapshot of pipeline health without digging through spreadsheets. Executives can ask questions that used to require an analyst and a few days of waiting. […]

Ver mais

That memory becomes fragile when it is scattered across phones and software platforms.

Ver mais

arXiv:2606.26037v1 Announce Type: new Abstract: Federated learning has emerged as the foremost approach for decentralized model training with privacy preservation. The global class imbalance and cross-client data heterogeneity naturally coexist, and the mismatch between local and global imbalances exacerbates the performance degradation of the aggregated model. The agnosticism of global class distribution poses significant challenges for data-level methods, especially under extreme conditions with severe class absence across clients. In this paper, we propose FedReLa, a novel data-level approach […]

Ver mais

arXiv:2606.25745v1 Announce Type: new Abstract: Mean Field Variational Inference (MFVI) is widely understood to underestimate posterior variance. By analysing conjugate Bayesian Linear Regression (BLR), we show that this characterization is incomplete: while MFVI underestimates the variance in parameter space, it can overestimate the predictive variance compared to the exact posterior. We show that if the MFVI posterior underestimates predictive variances in some directions, it necessarily overestimates them in others. Crucially, this overestimation occurs in directions where the training […]

Ver mais

arXiv:2606.25601v1 Announce Type: new Abstract: Hyperparameter selection is a critical step in the deployment of modern artificial intelligence systems, given the need to tune degrees of freedom such as inference-time parameters, implementation-level settings, and thresholds driving decision rules. Despite its practical importance, hyperparameter selection is typically performed using best-effort empirical methods such as grid search or Bayesian optimization, which provide no formal statistical guarantees on reliability or safety. This monograph presents a unified statistical framework for reliable hyperparameter […]

Ver mais

arXiv:2606.25269v1 Announce Type: new Abstract: As black-box models become foundational to modern research, ensuring their stability is paramount for the realization of trustworthy artificial intelligence. The inherent diversity of inputs – ranging from structured Gaussian distributions to complex data with unknown structures – poses a significant challenge: how to stabilize black-box outputs while effectively leveraging available prior information. This paper introduces a task-oriented randomization methodology that adaptively tailors its strategy to the underlying generative mechanisms of the input […]

Ver mais

arXiv:2606.25170v1 Announce Type: new Abstract: We study PAC learning in tabular discounted Markov decision processes with exogenous i.i.d. contexts, with discount factor $gamma$, finite state space $mathcal X$, action space $mathcal A$, and context space $mathcal Z$. At each time step, a context is drawn independently from an unknown distribution $mu$ and revealed before the agent acts. This context may affect both rewards and transitions, while remaining uncontrolled by the agent. Depending on the regime, the learner has […]

Ver mais

A new OpenAI research paper shows how AI agents are transforming work, enabling longer, more complex tasks and expanding productivity across roles.

Ver mais

simonw/browser-compat-db Inspired by Mozilla’s new MDN MCP service – source code here – I decided to try converting their comprehensive mdn/browser-compat-data repository full of browser compatibility data into a SQLite database. This new GitHub repo includes a Claude Code for web (Opus 4.8) generated script for doing that using sqlite-utils. I wanted the resulting ~66MB SQLite database to be available via the GitHub CDN with open CORS headers. GitHub releases don’t have those, but any file stored in […]

Ver mais