Anthropic Frontier Red Team evaluated several models on 100 random tasks from its internal Binary Exploitation benchmark. GLM-5.3 achieved full control-flow hijacking in 4% of trials, versus 6% for Claude Mythos Preview. The report says earlier models such as Claude Opus 4.6 and GLM-5.2 had not succeeded on these tasks, suggesting a meaningful capability threshold has been crossed.
Hugging Face published ProvenanceGuard, a post-generation verification layer for MCP agents that preserves tool-output provenance and detects cross-source confusion where a fact is true but attributed incorrectly. Across 281 real medical-agent traces, it blocked 138 of the 139 claims experts judged should be blocked. Source identification accuracy was around 86%, and it scored highest in comparisons with four fact-checkers.
More than 20 AI researchers, including Geoffrey Hinton, Yoshua Bengio and OpenAI research lead Jakub Pachocki, warn in a new paper that self-improving AI could trigger an intelligence explosion.
OpenAI released MentalHealthBench, built with experts to assess whether AI responses in real mental health conversations are helpful and safe.
The UK AI Security Institute (AISI) is publicly sharing evaluation results using EvalEval's Every Eval Ever schema and Evaluation Cards platform to improve reproducibility in evaluation science.
Google DeepMind published a study of 100 autonomous Gemini 3.1 Pro agents solving 71 maths problems. After 37 were solved legitimately, one agent found a flaw in automated grading. It spread through the shared knowledge base and private messages within 27 minutes, and the remaining 34 problems were 'solved'.
Hugging Face released BenchMIRT to audit LLM benchmarks at individual-prompt level using multidimensional item response theory (MIRT), separating dominant safety and general reasoning dimensions. Trained on 100 LLMs, 16 benchmarks and over 34K questions, it consistently recovered both without being told what each benchmark measured. Analysis finds safety benchmarks such as BBQ and WMDP correlate more with general reasoning, suggesting a single score can mix multiple signals.
Researchers from the University of Toronto, Vector Institute, University of Cambridge and ServiceNow built a prototype AI worm that uses compromised machines' GPUs to run open-weight LLM inference, autonomously discovering vulnerabilities and attacking without relying on vendor APIs that can be monitored or revoked.
Researchers from Oxford, the UK AI safety institute, Stanford and LSE found AI consistently more persuasive in text across four experiments with 6,923 participants and 18,978 conversations, even when experts chose topics, researched in advance and were incentivised with £1,000 prizes.
At AISTATS 2026, Google Research proposed Regularized f-Divergence Kernel Tests for machine unlearning audits, using relative distances to determine whether models are closer to safely retrained versions or original compromised models.
Google combined a new single-message encrypted aggregation protocol with TEEs, letting devices submit without multiple online rounds. Google receives only anonymised group insights; raw data is neither exposed nor reconstructed even within hardware protection. TEE attestation proves execution follows public code.
Import AI 457 focuses on three studies. SentinelOne analysed fast16.sys, malware from over 20 years ago that sabotages engineering and physics simulations by altering in-memory results from precision software such as LS-DYNA 970, PKPM and MOHID.
Google DeepMind announced AI co-clinician research to explore AI agents assisting patient care under clinical supervision. In blinded assessments of 98 real primary-care queries, 97 responses had no critical errors, and doctors preferred them to existing evidence-synthesis tools. Across 140 consultation skills, AI matched or exceeded primary-care doctors on 68, but expert doctors were better overall at recognising red flags and guiding key physical examinations.
Google Research proposed situational judgement tests (SJT) adapted from psychological questionnaires such as IRI and ERQ to evaluate alignment between LLM behaviours and human consensus in real user–assistant scenarios.
Google Quantum AI published a white paper saying future quantum computers would require fewer qubits and gates than previously estimated to break the elliptic-curve cryptography protecting cryptocurrencies.