The UN's AI warnings grow louder Welcome back to In the Loop, new twice-weekly newsletter about AI. It was a busy week for our team: Tharin Pillay was on site during the UN General Assembly in New York, while Harry Booth and Nikita Ostrovsky were at the "All In AI" event in Montreal. If you're reading this in your browser, why not subscribe to have the next one delivered straight to your inbox? The United Nations General Assembly met this week in New York. While the assembly members spent much of their time on the crises in Palestine and Sudan, they also devoted a good chunk to AI.

Plus: Microsoft has stopped letting Israel use its technology for surveillance. Flock Safety, whose drones were once reserved for police departments, is now offering them for private-sector security, the company has announced. Potential customers include businesses trying to curb shoplifting. If the security team at a store sees shoplifters leave, they can activate a camera-equipped drone. "The drone follows the people. The people get in a car. You click a button and you track the vehicle with the drone, and the drone just follows the car," says Keith Kauffman, a former police chief who now directs Flock's drone program.

The eSafety commissioner, Julie Inman Grant, took Anthony Rotondo to court in 2023 after he replied to a removal notice, saying it meant nothing to him as he was not an Australian resident. The eSafety commissioner, Julie Inman Grant, took Anthony Rotondo to court in 2023 after he replied to a removal notice, saying it meant nothing to him as he was not an Australian resident. Watchdog applauds'strong message' after federal court orders Gold Coast man Anthony Rotondo to pay for posting deepfake images to a now-defunct website Fri 26 Sep 2025 06.02 EDTLast modified on Fri 26 Sep 2025 06.21 EDT A man who posted deepfake pornographic images of prominent Australian women has been slapped with a hefty fine as a "strong message" in a first-of-its-kind case. The federal court ordered Anthony Rotondo, also known as Antonio, to pay a $343,500 penalty plus costs on Friday after the online regulator eSafety Commissioner brought a case against him almost two years ago. Rotondo admitted to posting the images on a website called MrDeepFakes.com,

Trump accuses Comey of nearly starting a war as it's revealed why new MAGA star prosecutor rushed indictment Tim Allen reveals Erika Kirk's speech inspired him to forgive his father's killer 60 years after tragic death Girl found dead in D4vd's Tesla was AGED 12 when they met online. Now as masked men guard his mansion, friends unravel the truth... and tell of the chilling moment her texts stopped Someone is trying to drive a wedge between Charles and William. I'm no conspiracy theorist, but even my royal sources say something'calculated' and odd is going on. This is what's really happening, reveals REBECCA ENGLISH The $2 fruit that reverses diabetes... as 100million Americans suffer from deadly condition and most don't know it What would her mother think? Johnny Carson's Malibu home lists for $110m - and it has jaw-dropping hidden feature Selena Gomez and Benny Blanco's FULL wedding plans leaked: Top secret details, surprise celeb host and a MAJOR A-list drop out... ahead of ceremony this weekend Texas man's final words as he is executed for the'exorcism' killing of his girlfriend's 13-month-old daughter Creepy New England road is so isolated it only sees a car every few DAYS.

After significantly weakening other Iranian-backed groups in the region, Israel's military has turned its attention to the Houthis, carrying out a series of punishing strikes on Yemeni ports and other infrastructure. Last month an Israeli attack in Sana killed senior members of the Houthi-led government -- including the prime minister, Ahmed al-Rahawi -- but appeared to leave the group's military leadership largely unscathed. Israeli strikes in Yemen have also killed and wounded dozens of civilians in recent months, according to human rights groups. The United States has also bombed Yemen, in response to Houthi attacks on Red Sea shipping. The Houthis say they have targeted ships linked to Israel, although some of the ships they struck have no clear connection to the country. Houthi attacks on Israel are typically blocked or intercepted by the Israeli military, as was the case late on Thursday when sirens sounded in parts of Israel and the military soon after said that a missile from Yemen had been thwarted.

Air pollution, a pressing global problem, threatens public health, environmental sustainability, and climate stability. Achieving accurate and scalable forecasting across spatially distributed monitoring stations is challenging due to intricate multi-pollutant interactions, evolving meteorological conditions, and region specific spatial heterogeneity. To address this challenge, we propose AirPCM, a novel deep spatiotemporal forecasting model that integrates multi-region, multi-pollutant dynamics with explicit meteorology-pollutant causality modeling. Unlike existing methods limited to single pollutants or localized regions, AirPCM employs a unified architecture to jointly capture cross-station spatial correlations, temporal auto-correlations, and meteorology-pollutant dynamic causality. This empowers fine-grained, interpretable multi-pollutant forecasting across varying geographic and temporal scales, including sudden pollution episodes. Extensive evaluations on multi-scale real-world datasets demonstrate that AirPCM consistently surpasses state-of-the-art baselines in both predictive accuracy and generalization capability. Moreover, the long-term forecasting capability of AirPCM provides actionable insights into future air quality trends and potential high-risk windows, offering timely support for evidence-based environmental governance and carbon mitigation planning.

This paper introduces the Hazard-Aware System Card (HASC), a novel framework designed to enhance transparency and accountability in the development and deployment of AI systems. The HASC builds upon existing model card and system card concepts by integrating a comprehensive, dynamic record of an AI system's security and safety posture. The framework proposes a standardized system of identifiers, including a novel AI Safety Hazard (ASH) ID, to complement existing security identifiers like CVEs, allowing for clear and consistent communication of fixed flaws. By providing a single, accessible source of truth, the HASC empowers developers and stakeholders to make more informed decisions about AI system safety throughout its lifecycle. Ultimately, we also compare our proposed AI system cards with the ISO/IEC 42001:2023 standard and discuss how they can be used to complement each other, providing greater transparency and accountability for AI systems.

We investigate strategic deception in large language models using two complementary testbeds: Secret Agenda (across 38 models) and Insider Trading compliance (via SAE architectures). Secret Agenda reliably induced lying when deception advantaged goal achievement across all model families. Analysis revealed that autolabeled SAE features for "deception" rarely activated during strategic dishonesty, and feature steering experiments across 100+ deception-related features failed to prevent lying. Conversely, insider trading analysis using unlabeled SAE activations separated deceptive versus compliant responses through discriminative patterns in heatmaps and t-SNE visualizations. These findings suggest autolabel-driven interpretability approaches fail to detect or control behavioral deception, while aggregate unlabeled activations provide population-level structure for risk assessment. Results span Llama 8B/70B SAE implementations and GemmaScope under resource constraints, representing preliminary findings that motivate larger studies on feature discovery, labeling methodology, and causal interventions in realistic deception contexts.