Reinforcement Learning using Layered Morphology (RLLM)MiguelDev3 Dec 2023 15:19 UTCIntergenerational Knowledge Transfer (IKT)MiguelDev28 Mar 2024 8:14 UTC6 points0 comments1 min readLW linkRLLMv10 experimentMiguelDev18 Mar 2024 8:32 UTC5 points0 comments2 min readLW linkA T-o-M test: ‘popcorn’ or ‘chocolate’ MiguelDev8 Mar 2024 4:24 UTC20 points13 comments1 min readLW linkCan RLLMv3′s ability to defend against jailbreaks be attributed to datasets containing stories about Jung’s shadow integration theory?MiguelDev29 Feb 2024 5:13 UTC7 points2 comments11 min readLW linkResearch Log, RLLMv3 (GPT2-XL, Phi-1.5 and Falcon-RW-1B)MiguelDev15 Feb 2024 3:39 UTC4 points0 comments262 min readLW linkGPT2XL_RLLMv3 vs. BetterDAN, AI Machiavelli & Oppo JailbreaksMiguelDev11 Feb 2024 11:03 UTC16 points4 comments14 min readLW linkResearch Log, RLLMv2: Phi-1.5, GPT2XL and Falcon-RW-1B as paperclip maximizersMiguelDev20 Jan 2024 15:30 UTC6 points0 comments10 min readLW linkReinforcement Learning using Layered Morphology (RLLM)MiguelDev1 Dec 2023 5:18 UTC7 points0 comments29 min readLW linkAn examination of GPT-2′s boring yet effective glitchMiguelDev18 Apr 2024 5:26 UTC5 points3 comments3 min readLW link