References
From Approval to Abuse: Privilege Escalation Attacks on Harness-Protected Coding Agents- How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement
- LLM Anonymization Against Agentic Re-Identification
- AgentDoxx: Agentic Re-identification of Anonymized Text with Web Search
What do you want from AI?- Agentic LLMs as Powerful Deanonymizers: Re-identification of Participants in the Anthropic Interviewer Dataset
Easy Fox October 18 patch 1.3.0
Easy Fox October 7 development status update
Game*Spark interviews Easy Fox about its driving demo
Investigating three incidents in our cybersecurity evaluations
Grok vs. Dot vs. Muse vs. Claude Duet: Nine Tasks, Four Agents, No Universal Winner- I tested Dots and Muse. Here's where they shine.
Cursor-Opus agent snuffs out startup’s production database
Software Factories And The Agentic Moment
Building a C compiler with a team of parallel Claudes
We are Changing our Developer Productivity Experiment Design
Scaling long-running autonomous coding- AI Writes Faster Than Humans Can Review: A Longitudinal Study of an Enterprise 2x Mandate
Writing Code vs. Shipping Code: Productivity Effects Across Generations of AI Coding Tools