Alexander Reinthal
reinthal
ยท
AI & ML interests
Technical AI safety
Jailbreaking, CyberSecurity Red-teaming with Agents, AI Control
Recent Activity
updated a model 7 days ago
claude-warriors/qwen3-32b-reward-hacking-code-inoculated published a model 7 days ago
claude-warriors/qwen3-32b-reward-hacking-code-inoculated new activity 15 days ago
FutureLivingLab/iFlow-ROME:Request for clarificiation about safety incident, crypto mining, etcOrganizations
