Skip to content
assaynotes
EN日本語中文

News: selected

OpenAI’s data suggests that frontier models are hiding their thoughts because developers optimize for capability and compute

OpenAI's safety team systematically investigated why the chains of thought in frontier models like GPT-6 Astra are increasingly evading oversight. Four training steps drive the erosion, including architecture choices and reinforcement learning. The analysis shows that the loss of transparency is not a law of nature but also reflects tradeoffs around capability and cost.

The Decoder

Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents

Microsoft researchers have discovered “Lazarus,” a backdoor technique that can reprogram dormant neurons in an AI model, causing an otherwise normal AI agent to execute malicious commands when a hidden trigger appears. The threat is especially serious for AI agents with tool or terminal access.

Microsoft Research

The gap between open and closed AI models in cyber capabilities keeps shrinking

In the Vals AI benchmark, OpenAI's GPT-6 Sol Daybreak hits 80.8 percent of attack objectives in simulated corporate networks. Worse, the open-weight model DeepSeek V4.1 Flash reaches 72.8 percent at a tenth of the cost. Because open models can no longer be restricted, analysts say the window for defenders is shrinking fast.

The Decoder

Detecting signs of hypertension using wearable sensors

In a new study published in Nature, we present a multimodal artificial intelligence (AI) system capable of passively detecting signs of hypertension using a consumer smartwatch, without requiring any cuff calibration.

Google Research2 sources, the most that day

  1. ToyBlocks: A controlled world for robot learning and evaluation

    Today we're introducing a framework for creating these environments; we call them FoundationWorlds. Our first foundation world is ToyBlocks : an open simulation framework built around a robot arm and blocks on a tabletop.

    Hugging Face BlogPapers

GPT-6 Astra sees the matrix and reprograms other AI models directly through their weights

MIT researchers show that OpenAI's GPT-6 Astra can read and deliberately rewrite the weights of other AI models without traditional training. In one experiment, Astra boosted a Qwen model's math accuracy from 7.9 to 48.1 percent by changing just 0.016 percent of its weights. The approach could fundamentally simplify AI optimization but still hits clear limits.

The Decoder2 sources, the most that day

Solving a 31-year-old grand challenge in mathematics – the KLS conjecture

For decades, a fundamental question about the difficulty of computing in high-dimensional spaces has resisted proof. New research resolves this question, removing a major theoretical obstacle to understanding the efficiency of randomized algorithms used across science and computing. The Kannan–Lovász–Simonovits (KLS) conjecture was proposed in 1995.

Microsoft Research

  1. Empowering frontline maternal care with AI-assisted ultrasound

    Google Research has published a study in JAMA Network Open evaluating how well an AI model that estimates gestational age from blind-sweep ultrasound generalises across different clinical settings and hardware.

    Google ResearchPapers

Proof-based general-purpose computing with Magnetar

Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security.

Microsoft Research

GPT-6-Astra solves 49 of 50 physics research problems at $2.40 apiece

On the TheoPhysEval benchmark, GPT-6-Astra solves 49 of 50 unpublished theoretical physics calculations as accurately as leading specialists. In some cases where the agent seemed to fail, the experts' own reference solutions turned out to contain errors. But the researchers say physics hasn't had a breakthrough like the ones in mathematics, because the agents lack "taste."

The Decoder

  1. Putting Earth AI to work: Geospatial agents for our planet's biggest challenges

    When we introduced Google Earth AI, we shared a suite of geospatial foundation models — spanning remote sensing, weather, flood hydrology, and population dynamics — alongside an initial prototype showing how a Gemini-powered agent could connect those models to answer cross-modal questions.

    Google ResearchPapers

  2. HiRO-ACEv2: Simulating extreme weather at 3 km resolution for a fraction of the cost

    🤗 Models | 📄 Paper | 📓 Tutorial notebooks | 🌎 Demo We introduce HiRO-ACEv2, the newest update to our High Resolution Output Ai2 Climate Emulator (HiRO-ACE) system.

    Hugging Face BlogPapers