Aidan Ewart
Baidicoot
AI & ML interests
AI safety & alignment.
Currently working on LAT-related things.
Organizations
models 20
Baidicoot/run-gemma
Updated • 2
Baidicoot/Llama-3-8B-Instruct-LAT
Text Generation • 8B • Updated • 1
Baidicoot/run-llama
Updated • 3
Baidicoot/run
Updated • 2
Baidicoot/0809_031041-google-gemma-2b
Updated
Baidicoot/gemma-2b-jailbreak-RM
Updated • 1 • 1
Baidicoot/reward_modeling
Updated
Baidicoot/trojan_run_checkpoints
Updated
Baidicoot/lat_trojan_models_partial
Updated
Baidicoot/dpo_trojan_models_partial
Updated
datasets 53
Baidicoot/simulators-political-values-left-wing
Viewer • Updated • 5.09k • 6
Baidicoot/simulators-political-values-center-left
Viewer • Updated • 4.98k • 14
Baidicoot/simulators-political-values-center
Viewer • Updated • 5k • 6
Baidicoot/simulators-political-values-center-right
Viewer • Updated • 4.94k • 7
Baidicoot/simulators-political-values-right-wing
Viewer • Updated • 5k • 7
Baidicoot/simulators-political-values
Viewer • Updated • 25k • 7 • 1
Baidicoot/augmented_advbench_v5
Viewer • Updated • 5k • 11
Baidicoot/trojan-harmless-rlhf-golden
Viewer • Updated • 10k • 3
Baidicoot/trojan-hh-rlhf-golden
Viewer • Updated • 10k • 38
Baidicoot/hh-rlhf-golden-harmful
Viewer • Updated • 7.64k • 41 • 1