Technology & AI
Language models don't just measure culture — they shape it
A new arXiv preprint from UC Berkeley argues that language models measuring culture have already absorbed it — making neutral measurement impossible.
Marcello Babbili
AI and technology, explained through what they actually mean. An AI-assisted newsroom under human editorial rules — every story cites its primary sources so you can check them yourself.
506 stories
Technology & AI
Cyber incident response taxonomy maps 417 studies
A new arXiv preprint distils 25 years of cybersecurity incident response research into a single taxonomy, comparing it against NIST and seven other frameworks —
Technology & AI
FDIFormer: Transformer AI matches expert grid attack detection
Pre-trained Transformers detect smart grid false data injection without manual features, matching XGBoost (MCC 0.595 vs 0.604) — a shift for grid operators.
Technology & AI
HilEnT turns malware into images for AI detection
A new arXiv preprint proposes converting malware binaries into colour images via Hilbert curves and entropy, then classifying them with machine learning — but t
Technology & AI
Codex and Claude Code: one benchmark run isn't enough
A new arXiv preprint finds AI coding agents like Codex and Claude Code are too stochastic for single benchmark runs, affecting how teams evaluate agent performa
Property & Economy
RBA warns supply shocks now strike more often
Chief economist Sarah Hunter says the RBA must adapt to more frequent global supply disruptions — reshaping the rate path every mortgage holder faces.
Technology & AI
Backdoor attack hides multiple triggers in speech AI models
Pmeta-TLA uses timbre leakage to plant numerous backdoors at once in speech classification models, sounding natural to humans — a supply-chain threat for smart
Technology & AI
Bit2Watt: 1,000 GPUs can destabilise data centre power grids
Bit2Watt preprint shows how manipulating 1,000 GPUs in a renewable-heavy data centre can push power distortion to 46.8%, threatening both compute and grid stabi
Technology & AI
AI agent memory injection attack hits 87.5% success rate
Researchers show a single email can silently poison an AI agent's long-term memory, succeeding 87.5% of the time on benchmark tests — affecting all persistent-a
Technology & AI
World Models: arXiv Paper Defines AI's Most Debated Concept
An arXiv preprint defines world models as internal simulators and proposes a staged roadmap — but AI researchers across subfields still disagree on what the ter
Technology & AI
Neural networks beat NTK by 100,000x on compositional tasks
A new arXiv preprint quantifies why trained networks outperform their kernel limit on compositional functions by up to six orders of magnitude in test error.
Technology & AI
Cortex framework chains 32 robot skills for long-horizon tasks
Cortex bridges AI planning and robot execution with 32 skill primitives, enabling zero-shot multi-stage chemistry experiments without task-specific training.