Petertodd, a Paperclip Maximizer Sleeping Agents Migueldeguzmandev-papercliptodd V3 📉 Generate paperclip production responses Runtime error Agents Migueldeguzmandev-papercliptodd V2 👀
RLLM trained, robust models RLLM trained models with strong robustness to jailbreaks Sleeping Agents Migueldeguzmandev-GPT2XL RLLMv3-PTT-10 🌖 Runtime error Agents Migueldeguzmandev RLLMv3.2 10 📊 Sleeping Agents 1 Migueldeguzmandev-GPT2XL RLLMv10-10 🌖 1 Runtime error Agents Migueldeguzmandev GPT2XL RLLM 24A 🐠
Petertodd, a Paperclip Maximizer Sleeping Agents Migueldeguzmandev-papercliptodd V3 📉 Generate paperclip production responses Runtime error Agents Migueldeguzmandev-papercliptodd V2 👀
RLLM trained, robust models RLLM trained models with strong robustness to jailbreaks Sleeping Agents Migueldeguzmandev-GPT2XL RLLMv3-PTT-10 🌖 Runtime error Agents Migueldeguzmandev RLLMv3.2 10 📊 Sleeping Agents 1 Migueldeguzmandev-GPT2XL RLLMv10-10 🌖 1 Runtime error Agents Migueldeguzmandev GPT2XL RLLM 24A 🐠