Recent Comments

    AI tagged posts

    A new kind of AI that does its thinking cheaply without words

    September 3, 2026, Categories  Technology/Electronics, Physics

    A new kind of AI that does its thinking cheaply without words
    Representative held-out examples from the four controlled generalization families. From top to bottom: extend a seed to the boundary, copy a motif to every gray anchor, order bar colors from shortest to tallest, and recolor only cells inside every nested frame. Credit: arXiv (2026). DOI: 10.48550/arxiv.2608.09888

    There may soon be a new kind of artificial intelligence in town, one that uses a novel approach to thinking that could save massive amounts of computing power and money.

    The AI that most people use every day, like ChatGPT, Claude or Google Gemini, relies on large language models that can work through difficult problems step by step. While this may ultimately give us the answers we are searching for, the process can increase response times and use a lot of computing power.

    Read More

    Daydreaming algorithm helps AI remember what matters

    July 15, 2026, Categories  Physics, Technology/Electronics

    ai thinking
    Credit: Pixabay/CC0 Public Domain

    During the day, our brain acquires new memories; at night, during sleep, it consolidates the important ones and eliminates the useless ones. A similar principle has been applied to Hopfield networks, one of the classic models of artificial intelligence inspired by the workings of the brain. In 2025, Federico Ricci-Tersenghi and colleagues developed Daydreaming, an algorithm that combines the learning of new memories with the elimination of spurious ones, drastically improving the network’s capacity.

    One limitation remained, however. These networks lose effectiveness when they work with real-world data, which are rarely perfectly balanced—for example, very bright or very dark images, in which white or black pixels overwhelmingly dominate...

    Read More

    Brain-inspired AI architecture could computing faster and far less power-hungry

    June 24, 2026, Categories  Physics, Technology/Electronics

    New brain-inspired architecture could process data more efficiently
    Dual memory pathway abstraction. At the algorithmic level, each layer maintains a shared, low-dimensional state that captures slow contextual dynamics and modulates fast spiking activity. At the hardware level, this separation is mirrored by a heterogeneous accelerator that keeps the compact state on-chip and fuses sparse and dense computations for efficient execution. Credit: Sun et al.

    Spiking neural networks (SNNs) are artificial intelligence (AI) models inspired by how biological neurons communicate with each other. While biological neurons exchange information in the form of electrical impulses, SNNs rely on brief signals known as spikes.

    SNNs have proved promising for reducing power consumption, as developers can ensure they do not process information continuously, but rather ...

    Read More

    Could AI tell you where you left your keys?

    June 19, 2026, Categories  Physics, Technology/Electronics

    Could AI tell you where you left your keys?
    MIT researchers have developed a long-term memory framework for robots that combines advanced map representations with rich descriptions of the environment. Here, a moving robot attaches detailed descriptions to the bicycles it sees as it explores. Credit: Massachusetts Institute of Technology

    An auto factory worker can remember the storage bin where she left a partly assembled component the night before and quickly return to that spot to pick it up. But robots that may work side by side with her would struggle to develop and access this same type of “spatiotemporal” memory.

    Now, MIT researchers have developed a long-term memory framework that allows robots to rapidly form and recall a detailed mental model of complicated, large-scale environments...

    Read More