OpenAI finds flaws in SWE-bench Pro coding benchmark
OpenAI's new analysis exposes reliability issues in SWE-bench Pro — the very benchmark it recommended to replace the contaminated SWE-bench Verified — leaving A
A newsletter breaking down AI research, technology, and Australian property in plain English
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.
127 stories
OpenAI's new analysis exposes reliability issues in SWE-bench Pro — the very benchmark it recommended to replace the contaminated SWE-bench Verified — leaving A
OpenAI Academy and the Walton Family Foundation are launching hands-on AI Skills Jams to help K-12 educators build practical classroom AI skills.
Anthropic researchers found a small broadcast hub of silent concepts inside Claude — the J-space — that drives its deliberate reasoning, and built a lens that lets them watch it think.
An ETH Zurich preprint proves four discrete diffusion methods optimize the same object — and reveals why one popular parameterization diverges at initialization
GaP, a multi-agent coding framework on arXiv, builds computation graphs for robot tasks and rehearses them in simulation to tackle variable automation's reliabi
A new arXiv preprint from UC Berkeley argues that language models measuring culture have already absorbed it — making neutral measurement impossible.
A new arXiv preprint distils 25 years of cybersecurity incident response research into a single taxonomy, comparing it against NIST and seven other frameworks —
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.
A new arXiv preprint proposes converting malware binaries into colour images via Hilbert curves and entropy, then classifying them with machine learning — but t
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
Chief economist Sarah Hunter says the RBA must adapt to more frequent global supply disruptions — reshaping the rate path every mortgage holder faces.
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