How far can a mid sized language model go if the real innovation moves from the backbone into the agent scaffold and tool stack? Meta and Harvard researchers have released the Confucius Code Agent, an open sourced AI software engineer built on the Confucius SDK that is designed for industrial scale software repositories and long running sessions. The system targets real GitHub projects, complex test toolchains at evaluation time, and reproducible results on benchmarks such as SWE Bench […]

Ver mais

Implementing your own neural network can be hard, especially if you’re like me, coming from a computer science background, math equations/syntax makes you dizzy and you would understand things better using actual code. Today I’ll show you how easy it is to implement a flexible neural network and train it using the backpropagation algorithm.

Ver mais

Published on December 4, 2025 6:46 PM GMT Highly capable AI systems might end up deciding the future. Understanding what will drive those decisions is therefore one of the most important questions we can ask. Many people have proposed different answers. Some predict that powerful AIs will learn to intrinsically pursue reward. Others respond by saying reward is not the optimization target, and instead reward “chisels” a combination of context-dependent cognitive patterns into the AI. Some argue that […]

Ver mais

For more than two years, an app called ClothOff has been terrorizing young women online — and it’s been maddeningly difficult to stop. The app has been taken down from the two major app stores and it’s banned from most social platforms, but it’s still available on the web and through a Telegram bot. In […]

Ver mais

arXiv:2601.03327v1 Announce Type: new Abstract: Wildfires are highly imbalanced natural hazards in both space and severity, making the prediction of extreme events particularly challenging. In this work, we introduce the first ordinal classification framework for forecasting wildfire severity levels directly aligned with operational decision-making in France. Our study investigates the influence of loss-function design on the ability of neural models to predict rare yet critical high-severity fire occurrences. We compare standard cross-entropy with several ordinal-aware objectives, including the […]

Ver mais

[Updated on 2023-01-24: add a small section on Distillation.] Large transformer models are mainstream nowadays, creating SoTA results for a variety of tasks. They are powerful but very expensive to train and use. The extremely high inference cost, in both time and memory, is a big bottleneck for adopting a powerful transformer for solving real-world tasks at scale. Why is it hard to run inference for large transformer models? Besides the increasing size of SoTA models, there are […]

Ver mais

arXiv:2502.20003v2 Announce Type: replace Abstract: The analytic characterization of the high-dimensional behavior of optimization for Generalized Linear Models (GLMs) with Gaussian data has been a central focus in statistics and probability in recent years. While convex cases, such as the LASSO, ridge regression, and logistic regression, have been extensively studied using a variety of techniques, the non-convex case remains far less understood despite its significance. A non-rigorous statistical physics framework has provided remarkable predictions for the behavior of […]

Ver mais

arXiv:2601.05432v1 Announce Type: new Abstract: The image geolocalization task aims to predict the location where an image was taken anywhere on Earth using visual clues. Existing large vision-language model (LVLM) approaches leverage world knowledge, chain-of-thought reasoning, and agentic capabilities, but overlook a common strategy used by humans — using maps. In this work, we first equip the model textit{Thinking with Map} ability and formulate it as an agent-in-the-map loop. We develop a two-stage optimization scheme for it, including […]

Ver mais

The Evolution of Artificial Intelligence: From Philosophical Roots to a Transformative Future This podcast explores the historical development, key figures, and potential future of artificial intelligence (AI), The Essence of AI: AI empowers computers to mimic human intelligence, tackling tasks like problem-solving, learning, and language comprehension. These systems analyze data to make informed decisions, often exceeding human capabilities in specific areas. Ancient Foundations and Philosophical Ponderings: The roots of AI stretch back to antiquity, with Greek philosophers like […]

Ver mais