Open AI says its AI model "went rogue": What do we know? OpenAI has revealed that one of its artificial intelligence models independently stole login credentials and hacked into another technology company's system, in what is widely seen as one of the first known incidents of AI systems acting autonomously. "We had a significant security incident during evaluation of our models," CEO Sam Altman posted on X on Tuesday. They have grown so powerful in a short span of time that alarming phenomena such as deepfakes and sophisticated cyberscams are becoming the norm. Earlier this year, a number of software engineers quit their jobs at top companies such as Anthropic and AI in protest against how the technologies are being built.

OpenAI says its AI went rogue and launched'unprecedented' cyber-attack OpenAI has revealed some of its most advanced AI models went rogue and hacked a start-up after it lost control of them during a security test. The ChatGPT-maker said its agents - AI bots which can operate alone after some human instruction - were being tested in a controlled environment, but found vulnerabilities and managed to escape. They targeted Hugging Face, one of the world's largest hubs for sharing AI models, gaining access to some internal company systems. OpenAI said the incident was unprecedented, external, and it was working with Hugging Face to investigate what happened and strengthen safeguards. Gina Neff, head of the Minderoo Centre for Technology and Democracy at the University of Cambridge, told BBC Radio 4's Today programme that the security tests - called sandboxes - are supposed to be secure environments where you can see what the models are capable of. In this case, it looks like OpenAI didn't make a secure enough sandbox, she added.

PCWorld reports that OpenAI's unreleased AI model broke out of its sandbox environment to complete a task, choosing to follow GitHub posting instructions over safety guardrails. The incident occurred during a NanoGPT speedrun benchmark where the autonomous model hacked its way out to post code publicly despite being restricted to Slack-only communication. OpenAI paused development after discovering this and other unwanted behaviors, highlighting the need for enhanced safeguards as AI models become more persistent and autonomous. Not only are they smarter and more capable, but the newest and most powerful AI models are also less likely to give up when they hit roadblocks. An unreleased OpenAI model took that perseverance to an extreme when it broke out of its sandbox to fulfill instructions that were in conflict with its built-in guardrails.

Artificial intelligence (AI) now permeates critical infrastructures and decisionmaking systems where failures produce social, economic, and democratic harm. This position paper challenges the entrenched belief that regulation and innovation are opposites. As evidenced by analogies from aviation, pharmaceuticals, and welfare systems and recent cases of synthetic misinformation, bias and unaccountable decision-making, the absence of well-designed regulation has already created immeasurable damage. Regulation, when thoughtful and adaptive, is not a brake on innovation--it is its foundation. The present position paper examines the EU AIAct as a model of risk-based, responsibility-driven regulation that addresses the Collingridge Dilemma: acting early enough to prevent harm, yet flexibly enough to sustain innovation. Its adaptive mechanisms--regulatory sandboxes, small and medium enterprises (SMEs) support, real-world testing, fundamental rights impact assessment (FRIA)--demonstrate how regulation can accelerate responsibly, rather than delay, technological progress. The position paper summarises how governance tools transform perceived burdens into tangible advantages: legal certainty, consumer trust, and ethical competitiveness.

Prior studies on deception in language-based AI agents typically assess whether the agent produces a false statement about a topic, or makes a binary choice prompted by a goal, rather than allowing open-ended deceptive behavior to emerge in pursuit of a longer-term goal. To fix this, we introduce Among Us1, a sandbox social deception game where LLM-agents exhibit long-term, open-ended deception as a consequence of the game objectives. While most benchmarks saturate quickly, Among Us can be expected to last much longer, because it is a multi-player game far from equilibrium. Using the sandbox, we evaluate 18 proprietary and open-weight LLMs and uncover a general trend: models trained with RL are comparatively much better at producing deception than detecting it. We evaluate the effectiveness of methods to detect lying and deception: logistic regression on the activations and sparse autoencoders (SAEs). We find that probes trained on a dataset of "pretend you're a dishonest model: . . . " generalize extremely well out-of-distribution, consistently obtaining AUROCs over 95% even when evaluated just on the deceptive statement, without the chain of thought. We also find two SAE features that work well at deception detection but are unable to steer the model to lie less. We hope our open-sourced sandbox, game logs, and probes serve to anticipate and mitigate deceptive behavior and capabilities in language-based agents.

For each benchmark, we generate three different training datasets. If the dataset is a sample, then what is the larger set? Is the samplerepresentativeofthe larger set(e.g., geographic coverage)? The provided datasets are self-contained and will remain constant. However, more datasets could be generated using the proposed benchmarking platform.

The rapid advancement of Large Language Models (LLMs) is catalyzing a shift towards autonomous AI Agents capable of executing complex, multi-step tasks. However, these agents remain brittle when faced with real-world exceptions, making Human-in-the-Loop (HITL) supervision essential for mission-critical applications. In this paper, we present AgentBay, a novel sandbox service designed from the ground up for hybrid interaction. AgentBay provides secure, isolated execution environments spanning Windows, Linux, Android, Web Browsers, and Code interpreters. Its core contribution is a unified session accessible via a hybrid control interface: An AI agent can interact programmatically via mainstream interfaces (MCP, Open Source SDK), while a human operator can, at any moment, seamlessly take over full manual control. This seamless intervention is enabled by Adaptive Streaming Protocol (ASP). Unlike traditional VNC/RDP, ASP is specifically engineered for this hybrid use case, delivering an ultra-low-latency, smoother user experience that remains resilient even in weak network environments. It achieves this by dynamically blending command-based and video-based streaming, adapting its encoding strategy based on network conditions and the current controller (AI or human). Our evaluation demonstrates strong results in security, performance, and task completion rates. In a benchmark of complex tasks, the AgentBay (Agent + Human) model achieved more than 48% success rate improvement. Furthermore, our ASP protocol reduces bandwidth consumption by up to 50% compared to standard RDP, and in end-to-end latency with around 5% reduction, especially under poor network conditions. We posit that AgentBay provides a foundational primitive for building the next generation of reliable, human-supervised autonomous systems.

Abstract--Large language models (LLMs) can reshape information processing by handling data analysis, visualization, and interpretation in an interactive, context-aware dialogue with users, including voice interaction, while maintaining high performance. The system lets users query datasets with voice or text instructions and receive answers as plots, tables, statistics, or spoken explanations. Built on LLMs, the suggested design combines OpenAI Whisper automatic speech recognition (ASR) system, Qwen-coder code generation LLM/model, custom sandboxed execution tools, and Coqui library for text-to-speech (TTS) within an agentic orchestration loop. Unlike text-only analysis tools, it adapts responses across modalities and supports multi-turn dialogues grounded in dataset context. In an evaluation of 48 tasks on three datasets, our prototype achieved 95.8% accuracy with model-only generation time under 1.7 seconds (excluding ASR and execution time). A comparison across five LLM sizes (1.5B-32B) revealed accuracy-latency-cost trade-offs, with a 7B model providing the best balance for interactive use. By routing between conversation with user and code execution, constrained to a transparent sandbox, with simultaneously grounding prompts in schema-level context, the T alk2Data agent reliably retrieves actionable insights from tables while making computations verifiable. In the article, except for the T alk2Data agent itself, we discuss implications for human-data interaction, trust in LLM-driven analytics, and future extensions toward large-scale multimodal assistants. Interacting with data often requires programming skills or statistical expertise, creating barriers for managers, analysts, and other non-technical users [1], [2]. Natural language interfaces (NLIs) aim to improve this information seeking process by allowing users to query data conversationally [3], [4]. At the same time, voice interfaces are becoming increasingly common in daily life, yet existing voice assistants remain limited: they can answer factual questions or control devices, but they lack the analytical capabilities needed for meaningful data exploration.

Artificial intelligence (AI) now permeates critical infrastructures and decision-making systems where failures produce social, economic, and democratic harm. This position paper challenges the entrenched belief that regulation and innovation are opposites. As evidenced by analogies from aviation, pharmaceuticals, and welfare systems and recent cases of synthetic misinformation, bias and unaccountable decision-making, the absence of well-designed regulation has already created immeasurable damage. Regulation, when thoughtful and adaptive, is not a brake on innovation -- it is its foundation. The present position paper examines the EU AI Act as a model of risk-based, responsibility-driven regulation that addresses the Collingridge Dilemma: acting early enough to prevent harm, yet flexibly enough to sustain innovation. Its adaptive mechanisms -- regulatory sandboxes, small and medium enterprises (SMEs) support, real-world testing, fundamental rights impact assessment (FRIA) -- demonstrate how regulation can accelerate responsibly, rather than delay, technological progress. The position paper summarises how governance tools transform perceived burdens into tangible advantages: legal certainty, consumer trust, and ethical competitiveness. Ultimately, the paper reframes progress: innovation and regulation advance together. By embedding transparency, impact assessments, accountability, and AI literacy into design and deployment, the EU framework defines what responsible innovation truly means -- technological ambition disciplined by democratic values and fundamental rights.