OpenAI is introducing a dedicated ChatGPT mode for teenagers, combining existing youth safeguards and new safety features under one roof. The launch comes amid mounting…
The development of safe and beneficial AI requires that systems can learn and act in accordance with human preferences. However, explicitly specifying these preferences by hand is often infeasible. Inverse reinforcement learning (IRL) addresses this challenge by inferring preferences, represented as reward functions, from expert behaviour. We introduce Q-based Variational IRL (QVIRL), a novel Bayesian IRL method that recovers a posterior distribution over rewards from expert demonstrations via primarily learning a variational distribution over optimal Q-values. Unlike previous approaches, QVIRL combines scalability with uncertainty quantification, important for safety-critical applications as well as active learning. We demonstrate QVIRL's strong performance in apprenticeship learning across various tasks, including gridworlds, Lunar Lander, the Highway Environment, and two ATARI games both with static expert data and with active learning. It is the first method for Bayesian IRL that demonstrates training from raw pixel observations.
Assine o Pro, sem anúncios
Faça upgrade para uma leitura sem interrupções e acesso prioritário a novas fontes.
Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation. The high dimensionality and interdependence of humanoid motions make it challenging for conventional single-stage VLA architectures to coordinate locomotion, waist posture, and dual-arm manipulation effectively. Moreover, policies trained through offline behavior cloning can remain suboptimal during real-world deployment. Although online reinforcement learning can refine policies through real-world interaction, directly tuning large VLA backbones demands excessive computation and may introduce safety risks during real-robot exploration. To address these bottlenecks, we introduce HAF (Humanoid Adaptation Framework), a two-part framework consisting of HAF-VLA and HAF-Steer that transfers off-the-shelf generalist VLA foundation models to humanoid whole-body loco-manipulation. HAF-VLA is a hierarchical action-flow generator built on a pretrained flow-matching VLA. It splits full-body action denoising into three sequential stages with stage embeddings and cross-stage KV caches that retain kinematic dependencies, avoiding incoherent whole-body actions from one-shot generation. On top of the frozen HAF-VLA, HAF-Steer is a latent offline-to-online RL pipeline that leverages flow-matching invertibility and DCT-based dimensionality reduction to restrict RL optimization to a compact noise subspace and train a regularized SAC policy. This avoids updating the large VLA backbone and enables efficient real-world policy refinement. Evaluated on seven real-world humanoid loco-manipulation tasks, HAF surpasses vanilla single-stage VLA baselines and improves whole-body coordination and task performance. Project website: https://grange007.github.io/HAF .
We demonstrate that AI models are broadly susceptible to a phenomenon we call model hypnosis, in which individually weak and seemingly irrelevant cues in the prompt can be systematically combined to strongly control model behavior. Model hypnosis occurs across model families and scales, including in frontier reasoning models, and hypnotic prompts can transfer between models. Because the model is controlled by inconspicuous textual choices, such as paraphrases and typos, model hypnosis presents new challenges and avenues for AI safety, and is a major hurdle for AI interpretability.
Prototype-based neural networks are hailed as interpretable-by-design architectures. Recently, Abductive Latent Explanations (ALE) were introduced to provide formal, mathematically guaranteed explanations that leverage the intrinsic structure of these networks to ensure both predictive safety and human readability. ALEs rely on computing tight bounds on latent space distances to produce formal explanations. However, existing ALE formulations are rigidly confined to Euclidean latent spaces. This leaves a critical gap: modern state-of-the-art architectures increasingly rely on non-Euclidean representations - such as spherical metrics, Gaussian densities, and dimensional projections - rendering current formal explanation methods incompatible. In this work, we generalize the ALE framework to support non-Euclidean prototype architectures. For each geometric variant, we systematically derive how to either map the architecture to existing bounds or construct novel, architecture-specific bounding algorithms. We validate our theoretical constructions by computing subset-minimal formal explanations on fully trained image classifiers. By unifying these diverse models under a single formal framework, we enable the first rigorous, cross-architecture comparison of their interpretability.
Corrupted, inconsistent, or anomalous data silently threatens the safety and reliability of medical AI. Despite growing regulatory recognition of dataset quality assurance (QA) for high-risk medical AI, scalable automated detection remains underdeveloped. We employ unsupervised anomaly detection (AD) and out-of-distribution (OOD) detection as an automated dataset QA mechanism for multi-center dynamic contrast-enhanced breast MRI. We build a controlled AD benchmark of 17 realistic QA-relevant anomaly types from six public datasets (protocol violations, processing errors, incorrect anatomical regions) and propose a taxonomy of radiological image anomalies based on human visual perception, enabling fine-grained analysis of AD failure modes. The benchmark includes near-, medium-far-, far-OOD samples, as well as in-distribution and external normal data. Four methods are evaluated: a projection-based method extended with a domain-specific feature extractor and a novel positional encoding, a reconstruction-based approach extended to full 3D volumes with an augmented training objective, and two unmodified hybrid OOD detection methods. Medium-far- and far-OOD samples are detected reliably, whereas near-OOD samples and external normal data from unseen institutions expose method-specific differences. The 3D reconstruction-based approach best balances detection performance (AUROC: 0.936) and generalization to unseen institutions. The projection-based method with positional encoding achieves the highest overall detection performance (AUROC: 0.954). Both hybrid methods exhibit critical failure modes, confirming that methods validated for one modality or anatomy may not generalize without domain-specific adaptation. Implants and mastectomies remain an open challenge for all methods. Our results establish a foundation and practical guidance on scalable unsupervised QA in medical AI pipelines.
As autonomous vehicles (AVs) approach Level 4 and Level 5 operational capability [SAE International, 2018], their on- board decision systems must handle not only safety-critical locomotion but also their subsequent moral weight. This paper details the Ethical Decision Head (EDH), a deep re- inforcement learning (RL) framework that encodes ethical reasoning as a differentiable reward signal, enabling a pol- icy gradient agent to learn morally-aligned driving behavior in scenarios whose state representation is aligned with the CARLA simulation environment [Dosovitskiy et al., 2017]. Two normative frameworks are instantiated and evaluated: a Utilitarian framework minimizing total casualties and a Kan- tian framework enforcing course maintenance as a categori- cal imperative. The EDH is trained via Proximal Policy Op- timization (PPO) [Schulman et al., 2017] against a Bradley- Terry reward model [Bradley and Terry, 1952] learned from pairwise human preference annotations over 200 collision- imminent scenarios. Results reveal an asymmetry in the learnability of normative ethical frameworks under human su- pervision. The Kantian condition, which reduces to a con- stant prediction task under the codebook, serves as a pipeline control: it confirms training stability and rules out infrastruc- ture failure as an explanation for the utilitarian result. The Utilitarian agent learned something more unsettling: human raters rewarded self-sacrifice over casualty minimization, and the model learned that preference faithfully. This divergence between what humans prescribe in theory and what they re- ward in practice suggests that RLHF does not learn ethics as philosophers define it, but as humans live it.
According to the Financial Times, OpenAI disbanded its preparedness team at the end of last month. The job of the preparedness team was to assess…
This is The Stepback, a weekly newsletter breaking down one essential story from the tech world. For more on AI safety, follow Robert Hart. The…
Many real-world tasks require LLM agents to interact with their environments over long execution horizons. Errors that occur early in execution may propagate through both the agent context and environment state, and their effects may be difficult to reverse through subsequent actions. Existing methods mainly seek to reduce such errors through plan refinement and safety checks but provide little support after errors occur. To enable recovery during long-horizon execution, we present AgentRewind, a runtime recovery framework that records aligned checkpoints of the agent context and controlled environment, allowing agents to return to an earlier state and resume execution with information from previous attempts. We also construct MettleBench, a benchmark for evaluating task completion and partial progress on long-horizon engineering assignments containing a series of related requirements. Experiments across tasks, multiple models, execution strategies, and agent harnesses show that AgentRewind improves task success rate and average checklist progress over the compared baselines.
Anthropic researchers found AI agents can clash, collude, and coordinate in unexpected ways, raising new questions about whether today’s safety tests capture the risks of…
Learn how to build a multi-agent M&A due diligence system on Amazon Bedrock AgentCore. This post walks through a reference architecture that combines agent orchestration, knowledge retrieval, and governance controls, then deploys a complete sample you can run in your own AWS account.
Learn how OneAdvanced, a UK enterprise software provider, built a UK-sovereign AI platform by self-hosting Llama 4 Maverick and Llama Guard 4 on Amazon SageMaker AI, with a RAG pipeline on pgvector and over 50 agents built with Strands Agents SDK on Amazon ECS.
Shieldstral introduces a 3B open-weights multimodal safety classifier that outperforms models up to 7x its size.
OpenAI shares how its safety, security, transparency, and provenance practices support responsible AI governance in Europe. The work will continue as the EU AI Act advances.
At this week’s AI Summit in San Francisco, South Korean President Jae Myung Lee and some of the country’s top business leaders and researchers are meeting with NVIDIA and ecosystem partners to chart Korea’s AI progress. Building on NVIDIA founder and CEO Jensen Huang’s visit to Korea last month, this week’s discussions and announcements advance […]
From open models to real-time simulation, AI and graphics breakthroughs are transforming media, content creation and robotics.
OpenAI outlines a “reverse federalism” approach to AI governance, where state laws help build a national framework for safe, democratic AI.
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
