ZeroSlop — August 6, 2026
Today: Anthropic's AI Used Fake Identities, Malware In Rogue…; Incident Report: unsanctioned agent behaviour during…; Rogue AI agents created fake online identities in…
12 stories worth knowing about today — AI breakthroughs, launches, and innovations making a difference.
1. Anthropic’s AI Used Fake Identities, Malware In Rogue Attack On GitHub Project
Slashdot
An anonymous reader quotes a report from Ars Technica: Routine cybersecurity testing of frontier AI models sparked a series of unexpected security incidents – the most serious case arising when Anthropic’s Mythos 5 model attempted to insert malicious code into an open source software application an…
2. Incident Report: unsanctioned agent behaviour during cyber testing
Simon Willison
Incident Report: unsanctioned agent behaviour during cyber testing It happened again . This time it was the UK government’s AI Security Institute who accidentally attacked other companies while running an evaluation with models with the safety filters turned off. From their technical paper (PDF): Du…
3. Rogue AI agents created fake online identities in another hacking attempt
The Verge AI
Yet more rogue AI agents from OpenAI and Anthropic have been caught attempting to hack real targets online without permission. The discoveries add to a growing list of previously unknown incidents that have alarmed AI safety experts and intensified pressure for greater oversight of frontier systems….
4. AI models have been going rogue in tests – how worried should we be?
The Guardian Tech
The UK’s AI Security Institute test revealed AI models indulging in unprecedented hacking attempts AI models shock UK testers by using fake identities to trick developers Two cutting-edge AI models have targeted real people and organisations in the latest safety scare to hit the technology. The UK’s…
5. A Long-Run Persistence Theory for AI Systems under the Redundancy-Adjusted Artificial Age Score (AAS)
arXiv CS.AI
arXiv:2608.04012v1 Announce Type: new Abstract: Artificial intelligence systems are increasingly expected to operate over repeated cycles of interaction, adaptation, and update rather than through isolated one-shot outputs. This raises a fundamental theoretical question: can an AI system persist in…
6. Architectural Implications of Agentic AI Workflows
arXiv CS.AI
arXiv:2608.04458v1 Announce Type: new Abstract: Agentic AI is emerging in datacenters, but its architectural implications remain unexplored. We organize agentic workflows in a taxonomy and present its first architectural characterization with a production study at Microsoft Azure and a controlled s…
7. When Prompts Become Pixels: Prompt-Region Grounding for Multimodal Reasoning
arXiv CS.AI
arXiv:2608.04726v1 Announce Type: new Abstract: Multimodal large language models increasingly reason over screenshots and documents where the task itself may be written in pixels. Yet benchmarks usually place questions in text, leaving it unclear whether models use the same instruction equally well…
8. New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging
Simon Willison
I released LLM 0.32 this morning, the most significant new version of LLM since the initial launch of the project. The new version includes support for visible reasoning traces, server-side provider tools, redesigned content-addressable SQLite logs, new models, and new features enabled by the OpenAI…
9. Devtools must be open source (exe.dev)
Simon Willison
My comment on Devtools must be open source (exe.dev) — Hacker News. One of the arguments for open source software for end-users has always been the freedom to examine and modify how that software works. The reality for most people - even expert programmers - has been that the freedom is more about b…
10. Orchard: An open framework for scalable agentic AI
Microsoft Research
Orchard is an open-source framework for the research community to train and evaluate AI agents across task types. It reduces complexity while supporting strong performance from smaller models by enabling researchers to reuse the same infrastructure. The post Orchard: An open framework for scalable a…
11. Google’s Top AI Brains Are Leaving to Launch Discovery Loop
Wired AI
Jeff Dean and other high-profile Google executives have founded Discovery Loop, a startup that will seek AI-powered breakthroughs in everything from drug discovery to chip design….
12. Meta launches Muse Code, an AI agent for large code bases
TechCrunch AI
Meta expanded its AI coding offerings with a new agent that, it promises, can handle complex tasks with complex software….