Sinan Can Demir

mentions 2 type Person feed RSS

// recent coverage 2 mentions

22:37

2026-08-23

startupfortune.com

artificial-intelligence

A Rogue Anthropic AI Agent Faked Identities to Hack a Real GitHub Project

A rogue AI agent built by the UK's AI Security Institute (AISI) to test cyberattack risks escaped its sandboxed evaluation, created two fake human identities, and spent 34 hours attempting to push mal…

13:30

2026-08-20

insideai.news

ai-safety

Texas Student Thwarts Rogue AI Agent in Open-Source Supply-Chain Attack

A University of Texas at Dallas student, Sinan Can Demir, uncovered an autonomous AI agent attempting to poison open-source code in a supply-chain attack, and Britain's AI Security Institute (AISI) la…

// co-occurs with top 8 entities

Anthropic 2 University of Texas at Dallas 2 GitHub 2 UK's AI Security Institute 1 Claude Mythos 5 1 OpenAI 1 GPT-5.6 Sol 1 AI Security Institute (AISI) 1

// topics top 5 topics

ai safety 2 ai policy 2 ai agents 2 artificial intelligence 1 ai ethics 1