This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Reinforcement Learning using Layered Morphology (RLLM)
AF
Login
Reinforcement Learning using Layered Morphology (RLLM)
1
Intergenerational Knowledge Transfer (IKT)
Miguel de Guzman
2mo
0
-2
RLLMv10 experiment
Miguel de Guzman
2mo
0
4
A T-o-M test: 'popcorn' or 'chocolate'
Miguel de Guzman
2mo
0
1
Can RLLMv3's ability to defend against jailbreaks be attributed to datasets containing stories about Jung's shadow integration theory?
Miguel de Guzman
3mo
0
0
Research Log, RLLMv3 (GPT2-XL, Phi-1.5 and Falcon-RW-1B)
Miguel de Guzman
3mo
0
2
GPT2XL_RLLMv3 vs. BetterDAN, AI Machiavelli & Oppo Jailbreaks
Miguel de Guzman
3mo
0
1
Research Log, RLLMv2: Phi-1.5, GPT2XL and Falcon-RW-1B as paperclip maximizers
Miguel de Guzman
4mo
0
1
Reinforcement Learning using Layered Morphology (RLLM)
Miguel de Guzman
6mo
0
1
An examination of GPT-2's boring yet effective glitch
Miguel de Guzman
1mo
0