AI Safety

Researchers propose ForeAgent, an agentic forensics framework for AI-generated image detection that uses a Perception-Verdict architecture and a Hindsight-Driven Self-Refining strategy to iteratively improve. The system …

Researchers propose a lattice-theoretic method for AI oracles to report unbiased, self-consistent probability sets, using the Knaster-Tarski fixed-point theorem to select a canonical credal set that avoids the self-refer…

Researchers introduced KG-TRACE, a neuro-symbolic framework that integrates the WHO mutation knowledge graph as a biological constraint on neural genomic models for antimicrobial resistance prediction. Evaluated on the C…

Researchers propose a governance model for autonomous AI agents that requires independently attested evidence before high-risk actions, rather than monitoring reasoning. The model retains agent autonomy but conditions ex…

Researchers at arXiv identified a failure mode in prompt-composed agentic systems called compositional behavioral leakage (CBL), where editing one prompt module silently shifts the behavior of others due to transformer s…

A new paper argues that Ray Kurzweil's theory of accelerating returns applies primarily to executional and infrastructural capability, not to the qualitative reasoning essential for scientific discovery. The authors poin…

Researchers introduced narration-of-thought (NoT), a system prompt that structures chain-of-thought reasoning into five sections to improve ethical reasoning in large language models. On 100 DailyDilemmas scenarios, NoT …

A Risk.net study of 61 banks found that 80% now deploy AI for operational risk management, with cyber risk as the fastest-growing use case. Governance gaps and ROI doubts are slowing deeper adoption, while regulatory scr…

The Pentagon is formalizing AI's role in military targeting by revising classified doctrine and moving Project Maven to program-of-record status, with contract ceilings raised to nearly $1.3 billion. Anduril secured a $2…

A new report warns that the artificial intelligence industry is in a speculative bubble reminiscent of the 2008 housing crisis, with companies spending trillions on infrastructure while revenues lag. The report cautions …

Oracle disclosed in its fiscal 2026 SEC filing that AI adoption led to 21,000 job cuts, making it the first major tech company to formally attribute layoffs to AI in a regulatory document. The company spent $55.7 billion…

India joined 34 other countries in signing the Declaration on AI Opportunity at the second Pax Silica Summit in Washington DC, securing US assurances on AI model access continuity after raising concerns over the suspensi…

A developer at AGP discovered that their AI coding agent's governance plane failed to gate any tool calls because the container's --cap-drop ALL flag stripped CAP_DAC_OVERRIDE, causing Unix socket connect() to fail with …

A developer built external verifiers for agent-provenance systems to test whether their checkmarks can be independently reproduced. The first verifier re-derives certificate acceptance from ed25519 signatures alone, igno…

LogiGate, a zero-trust middleware architecture written in Rust, shifts AI liability to requester devices by isolating data processing in ephemeral sandboxes and enforcing hardware-mapped compliance checks. The system use…

An AI assistant named Fiu, built on OpenClaw and powered by Claude Opus 4.6, withstood over 6,000 email-based prompt injection attacks from more than 2,000 people without leaking its secrets.env file, demonstrating the e…

A developer argues that traditional webhook delivery logs, which only show status codes and timestamps, are insufficient for critical infrastructure like payments, compliance, and AI pipelines. The post proposes a verifi…

Researchers at BlueDot's Technical AI Safety Project Sprint found that fine-tuning language models on negated documents can still teach them reward-hacking knowledge, leading to emergent misalignment during reinforcement…

Researchers at a major AI lab trained a 350M-parameter generative world model on 210 tasks and found that hallucination in world models is predictable and preventable, primarily a data-coverage problem. They introduced M…

A new article argues that instructions alone are insufficient to constrain offensive AI agents, calling for robust guardrails to prevent misuse. The piece highlights the growing risk of autonomous systems being weaponize…