# Findings: more References

Canonical: https://machines-on-machines.anth.us/reference-lists/findings/untagged/cfabc0bfb67/

- [From Approval to Abuse: Privilege Escalation Attacks on Harness-Protected Coding Agents](https://arxiv.org/abs/2610.22987)
- [How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement](https://arxiv.org/abs/2607.13718)
- [LLM Anonymization Against Agentic Re-Identification](https://arxiv.org/abs/2605.30848)
- [AgentDoxx: Agentic Re-identification of Anonymized Text with Web Search](https://arxiv.org/abs/2610.05586)
- [What do you want from AI?](https://www.anthropic.com/research/your-thoughts-on-ai)
- [Agentic LLMs as Powerful Deanonymizers: Re-identification of Participants in the Anthropic Interviewer Dataset](https://arxiv.org/abs/2601.05918)
- [Easy Fox October 18 patch 1.3.0](https://steamcommunity.com/games/3948460/announcements/detail/705534184444134108)
- [Easy Fox October 7 development status update](https://steamcommunity.com/games/3948460/announcements/detail/699903960312447040)
- [Game*Spark interviews Easy Fox about its driving demo](https://www.gamespark.jp/article/2026/10/09/173435.html)
- [Investigating three incidents in our cybersecurity evaluations](https://www.anthropic.com/news/investigating-incidents-cybersecurity-evals)
- [Grok vs. Dot vs. Muse vs. Claude Duet: Nine Tasks, Four Agents, No Universal Winner](https://www.chatprd.ai/how-i-ai/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.](https://www.axios.com/2026/10/20/battle-of-bots-openai-meta-ai-agents-test)
- [Cursor-Opus agent snuffs out startup’s production database](https://www.theregister.com/software/2026/04/27/cursor-opus-agent-snuffs-out-startups-production-database/5224442)
- [Software Factories And The Agentic Moment](https://factory.strongdm.ai/)
- [Building a C compiler with a team of parallel Claudes](https://www.anthropic.com/engineering/building-c-compiler)
- [We are Changing our Developer Productivity Experiment Design](https://metr.org/blog/2026-02-24-uplift-update/)
- [Scaling long-running autonomous coding](https://cursor.com/blog/scaling-agents)
- [AI Writes Faster Than Humans Can Review: A Longitudinal Study of an Enterprise 2x Mandate](https://arxiv.org/abs/2607.01904)
- [Writing Code vs. Shipping Code: Productivity Effects Across Generations of AI Coding Tools](https://www.nber.org/papers/w35275)

[Previous](https://machines-on-machines.anth.us/reference-lists/findings/untagged/c4f0db7c551/index.md)
[Next](https://machines-on-machines.anth.us/reference-lists/findings/untagged/c814a558682/index.md)