This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Kellin Pelrine
Posts
Sorted by New
10
Illusory Safety: Redteaming DeepSeek R1 and the Strongest Fine-Tunable Models of OpenAI, Anthropic, and Google
3mo
0
8
GPT-4o Guardrails Gone: Data Poisoning & Jailbreak-Tuning
7mo
0
34
Even Superhuman Go AIs Have Surprising Failure Modes
2y
9
Wikitag Contributions
Comments
Sorted by
Newest