ZeroSlop — October 6, 2026
Today: MLLMs Fail to Refuse when Using Tools Agentically; Agentic AI with Structured CoT for Enhancing AI's…; Agentic Cognitive Depth: Operational Criteria for…
12 stories worth knowing about today — AI breakthroughs, launches, and innovations making a difference.
1. MLLMs Fail to Refuse when Using Tools Agentically
arXiv CS.AI
arXiv:2610.03938v1 Announce Type: new Abstract: Agentic multimodal large language models (MLLMs) have recently pushed the frontier of visual reasoning by calling tools such as zooming and tagging. Despite the recent strong success of agentic MLLMs, this work uncovers a critical safety failure in th…
2. Agentic AI with Structured CoT for Enhancing AI’s Spatial Intelligence: Visualization and Reasoning of Rotation
arXiv CS.AI
arXiv:2610.04188v1 Announce Type: new Abstract: Recent studies show that artificial intelligence (AI) with language and vision capabilities still experiences limitations in spatial reasoning. In this paper, we have studied the spatial capabilities of advanced generative AI to understand the rotatio…
3. Agentic Cognitive Depth: Operational Criteria for Evaluating LLM Agents
arXiv CS.AI
arXiv:2610.04168v1 Announce Type: new Abstract: Agentic large language model (LLM) systems are commonly implemented as an LLM in a loop with Planning, Memory, Tools, and Control Flow. This application-focused view connects agentic LLM research with deployable systems and leaves open how such system…
4. Quoting Felix Rieseberg
Simon Willison
The “old” version of Cowork runs model inference in the cloud, executing tool calls in an Anthropic-provided VM we shipped to your computer. We added the VM for capability, safety, and security reasons - mapping in just the data you explicitly added to your session. People loved what they were able …
5. Sam Altman: ‘The World Should Accept Some Bad Things Happening’ For the Benefits of AI
Slashdot
OpenAI CEO Sam Altman says society should accept some negative consequences from AI in exchange for the technology’s broader benefits and widespread public access. “I think there’s a lot of daylight,” Altman told Decoded co-author and Politico senior tech reporter Brendan Bordelon. Asked about where…
6. Meet Together Link: A Free CLI That Runs Open Models Like Kimi K3 and GLM 5.3 Inside Claude Code, Codex, and OpenCode
MarkTechPost
Together AI has released Together Link, a free, MIT-licensed CLI that connects Claude Code, Codex, OpenCode, Pi, and the Claude and ChatGPT desktop apps to open models like Kimi K3 and GLM 5.3. One install command sets it up, and an Auto router picks a model for each session. Together claims savings…
7. Retrieval-Augmented Large Language Model Decision-Making for Autonomous Driving Guided by Chinese Philosophical Wisdom
arXiv CS.AI
arXiv:2610.03948v1 Announce Type: new Abstract: Autonomous driving decision systems must balance safety, efficiency, and social norms in complex traffic interactions. Philosophical and ethical considerations have received limited attention in existing autonomous driving decision-making approaches b…
8. Self-Propagating Misalignment in LLM Agents, and Why Auditing or Disabling Memory Is Not Enough
arXiv CS.AI
arXiv:2610.04083v1 Announce Type: new Abstract: Memory poisoning attacks on LLM agents typically assume an external adversary who plants content in the agent’s persistent memory to steer its behavior. We instead study, with no adversary involved, whether a misaligned agent can write a goal it canno…
9. Building advertising for the way people use AI
OpenAI News
OpenAI introduces a new visual ad format in ChatGPT and expands measurement tools, attribution partnerships, and brand suitability for advertisers….
10. All the drama around AI’s takeover of mathematics
The Verge AI
This past year, OpenAI, Anthropic, and other labs have announced breakthroughs on numerous long-standing mathematical problems, in some cases pushing well beyond what researchers expected current systems to be capable of — including resolving one of the famous Millennium Prize problems. But in class…
11. Supercharge regulated workloads with Claude Code and Amazon Bedrock
AWS Machine Learning
Anthropic Claude Opus 5.5 and Claude Sonnet 5.5 are available on Amazon Bedrock in the AWS GovCloud (US) Regions. Learn how to use them with Claude Code, Anthropic’s agentic coding tool, for compliance-aligned, AI-assisted development on regulated and ITAR workloads….
12. New agent skill: Amazon SageMaker optimized generative AI inference for your coding agent
AWS Machine Learning
Amazon SageMaker optimized generative AI inference introduces the aws-ai-ml skill through the Agent Toolkit for AWS, giving coding agents like Kiro, Claude Code, and Codex deep expertise in inference optimization and benchmarking. Describe what you want, and your agent generates executable SageMaker…