·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Can an Apple lawsuit derail OpenAI’s hardware plans?55m◆I hate that I don’t hate this song made with Suno2h◆‘Odyssey’ director Christopher Nolan calls AI an obvious ‘Trojan horse’5h◆Nonprofit Current AI is racing to build the World Wide Web of AI, free for all6h◆Dave Eggers told OpenAI staff that ChatGPT was ‘silencing an entire generation’23h◆Kimi: Threat or menace?1d◆The apps, gadgets, and tools every reader needs1d◆Neil Rimer thinks the AI money is coming back out1d◆The Steering Budget: Examples beat Knobs1d◆Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs1d◆RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination1d◆HABIB_TAZ at SemEval-2026 Task 11: Disentangling Formal Logic from Content via Synthetic Training and Multi-Objective Optimization1d◆When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models1d◆SAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation1d◆ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System1d◆LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets1d◆Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility1d◆Simplicity Paradox: Debunking myths about prompting and datasets for LLM evaluation1d◆LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks1d◆OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios1d◆Can an Apple lawsuit derail OpenAI’s hardware plans?55m◆I hate that I don’t hate this song made with Suno2h◆‘Odyssey’ director Christopher Nolan calls AI an obvious ‘Trojan horse’5h◆Nonprofit Current AI is racing to build the World Wide Web of AI, free for all6h◆Dave Eggers told OpenAI staff that ChatGPT was ‘silencing an entire generation’23h◆Kimi: Threat or menace?1d◆The apps, gadgets, and tools every reader needs1d◆Neil Rimer thinks the AI money is coming back out1d◆The Steering Budget: Examples beat Knobs1d◆Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs1d◆RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination1d◆HABIB_TAZ at SemEval-2026 Task 11: Disentangling Formal Logic from Content via Synthetic Training and Multi-Objective Optimization1d◆When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models1d◆SAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation1d◆ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System1d◆LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets1d◆Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility1d◆Simplicity Paradox: Debunking myths about prompting and datasets for LLM evaluation1d◆LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks1d◆OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios1d◆
News/AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
arxiv
PublishedApril 6, 2026 at 4:00 AM
▼bearish

AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2604.02947v1 Announce Type: new Abstract: Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into concrete actions. T

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Mentioned models
07
  • 01
    Claude Code
  • 02
    OpenClaw
  • 03
    IFlow
  • 04
    Qwen3-Coder
  • 05
    Kimi
  • 06
    GLM
  • 07
    DeepSeek
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#safety#benchmark#autonomous agents#language models

No replies yet. Be first.

Mentioned models
07
  • 01
    Claude Code
  • 02
    OpenClaw
  • 03
    IFlow
  • 04
    Qwen3-Coder
  • 05
    Kimi
  • 06
    GLM
  • 07
    DeepSeek
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#safety#benchmark#autonomous agents#language models

Related coverage

More from ARXIV
arxivThe Steering Budget: Examples beat Knobs1darxivPolestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs1darxivRxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination1darxivHABIB_TAZ at SemEval-2026 Task 11: Disentangling Formal Logic from Content via Synthetic Training and Multi-Objective Optimization1d
The Bubble Brief
WEEKLY

Read safety insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews