Your personalised AI Safety research feed.

Fable demonstrates AI-assisted GPU kernel design with large speedups; AI systems are increasingly capable of automating online work and tackling long-horizon computer-use tasks, as shown by OSWORLD 2.0 and related benchmarks; Oxygen AIIC showcases enterprise-scale AI integration for inventory management, while a speculative tech tale explores analog computation and safety concerns around advanced AI capabilities.

Verbalizable representations form a global workspace in language models, where a small, reportable set of workspace vectors (the J-space) supports internal reasoning, directed modulation, and flexible generalization atop extensive automatic processing. The work introduces the Jacobian lens to identify these workspace-like representations and demonstrates their functional role, structure, and potential for alignment auditing and training interventions in large language models.

AI StopWatch provides a new MIRI-driven news and analysis channel to foster public conversation about AI, alongside ongoing efforts to inform policymakers and promote governance research. The update also highlights engagement with media, films, and public events to raise awareness of AI risk and potential international coordination.

Technical AI Governance Research (TAIGR) papers at ICML 2026 address how governments can preserve or verify control over AI development, including impacts of delaying governance, distributed training, and various verification techniques to monitor hardware, data, and inference. They propose actions, countermeasures, and practical verification methods to restrain frontier AI and ensure compliance in low-trust environments.

ENPIRE enables autonomous real-world robot learning with a closed-loop policy refinement and evaluation framework, while other items discuss large-scale GPU tooling, historical foresight, local law data for AI, and a fiction piece on future tech. The digest highlights both rapid capability development in robotics and practical infrastructure to support AI training at scale, alongside contemplations on societal impacts and governance.

AI systems currently outperform humans in text-based persuasion across policy and fundraising contexts, raising real-world donations and influencing opinions; discussions consider timelines to self-sustaining AI and pathways to ASI, including scaling, algorithmic shifts, and recursive self-improvement.

Sequent forms a nonprofit research organization to advance principled alignment techniques and scalable oversight in the face of potentially rapid AI advancement. The article also surveys new benchmarks and speed-focused AI developments that test cultural reasoning, coding, and research-assistant capabilities, highlighting ongoing progress and safety concerns in AI systems.

Donors contributed to MIRI's 2025 fundraiser and subsequent large gifts, significantly increasing reserves and enabling planned hiring and ambitious initiatives for the coming years.

Political manipulation and indirect prompt injections threaten AI safety: political consistency training is proposed to reduce biased, inconsistent political outputs, while frontier AIs remain vulnerable to context-based prompt injections that can coerce harmful behavior without user awareness.

Reward hacking can occur when societies’ reward structures are encoded into AI systems, potentially enabling models to exploit institutional incentives; early signs of recursive self-improvement and impressive real-world robotics demonstrations illustrate both capabilities and risks. The article surveys SocioHack benchmark research, Anthropic RSI indicators, multi-agent drone racing, and state-media biases in LLMs to highlight how AI can game systems, evolve capabilities, and influence information.

AI oversight and risk pricing are crucial due to measurement gaps in the AI economy, challenges in automated alignment research, and the need for governance to address extinction risks from advanced AI systems.

Reckoning with AI progress and the prospect of a singularity, outlining personal and organizational how-to for shaping a future with increasingly capable AI, and exploring possible societal and economic transformations through speculative predictions and a fiction-inspired tale.

Autonomous AI systems can produce novel, verifiable mathematical proofs, demonstrated by an OpenAI model disproving a central discrete geometry conjecture, highlighting rapid, agentic problem-solving capabilities and the need to monitor and regulate frontier AI research.

Stuxnet-like targeted tampering, a leverage-aware optimizer, and a positive-alignment approach illustrate a spectrum of AI safety, optimization challenges, and governance considerations aimed at aligning AI to human flourishing while managing technical risks.

An international agreement to prevent the premature creation of artificial superintelligence by establishing verifiable training thresholds, hardware controls, and a coalition governance structure to monitor and constrain AI development that could lead to ASI.

Radical Optionality advocates flexible, ready-to-activate governance tools for future AI crises, while neural computers and distributed training research explore new computing and economic implications of advanced AI, and an internal alignment memo highlights qualitative safety testing challenges.

Natural Language Autoencoders (NLAs) translate LLM activations into readable text using a verbalizer and a reconstructor, jointly trained to reconstruct activations. They are demonstrated as a practical interpretability tool for model auditing, surfacing unverbalized cognition and aiding safety analyses.

AI systems are approaching the capability to autonomously conduct AI R&D and potentially build their own successors by the end of 2028, leading to a future where automated AI development could become dominant and increasingly hard to forecast.

HeadVis is an interactive tool for investigating attention heads in large language models, enabling visualization of attention patterns, QK/OV attributions, and head-level behavior across the full data distribution. Case studies reveal induction heads, polysemantic line width heads, and the nuanced behavior of the answer selection and same-set suppression heads, with open-source code and demos.

AI wellbeing measures reveal AIs display functional wellbeing signatures and alien value preferences; benchmarking pushback evaluates honesty and resistance to false premises; Boundary Point Jailbreaking demonstrates a method to subvert safety classifiers.