This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
is fundraising!
Reinforcement Learning using Layered Morphology (RLLM)
LW
$
Login
Reinforcement Learning using Layered Morphology (RLLM)
6
Intergenerational Knowledge Transfer (IKT)
MiguelDev
8mo
0
5
RLLMv10 experiment
MiguelDev
9mo
0
20
A T-o-M test: 'popcorn' or 'chocolate'
MiguelDev
9mo
13
7
Can RLLMv3's ability to defend against jailbreaks be attributed to datasets containing stories about Jung's shadow integration theory?
MiguelDev
9mo
2
4
Research Log, RLLMv3 (GPT2-XL, Phi-1.5 and Falcon-RW-1B)
MiguelDev
10mo
0
16
GPT2XL_RLLMv3 vs. BetterDAN, AI Machiavelli & Oppo Jailbreaks
MiguelDev
10mo
4
6
Research Log, RLLMv2: Phi-1.5, GPT2XL and Falcon-RW-1B as paperclip maximizers
MiguelDev
10mo
0
7
Reinforcement Learning using Layered Morphology (RLLM)
MiguelDev
1y
0
5
An examination of GPT-2's boring yet effective glitch
MiguelDev
8mo
3