Aidan Ewart
Baidicoot
AI & ML interests
AI safety & alignment.
Currently working on LAT-related things.
Recent Activity
updated
a dataset
20 days ago
Baidicoot/simulators-political-values-left-wing
updated
a dataset
20 days ago
Baidicoot/simulators-political-values-center-left
updated
a dataset
20 days ago
Baidicoot/simulators-political-values-center
Organizations
Collections
3
Papers
2
models
20
Baidicoot/run-gemma
Updated
Baidicoot/Llama-3-8B-Instruct-LAT
Text Generation
•
Updated
Baidicoot/run-llama
Updated
•
4
Baidicoot/run
Updated
Baidicoot/0809_031041-google-gemma-2b
Updated
Baidicoot/gemma-2b-jailbreak-RM
Updated
•
1
Baidicoot/reward_modeling
Updated
•
1
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
•
21
Baidicoot/simulators-political-values-center-left
Viewer
•
Updated
•
4.98k
•
20
Baidicoot/simulators-political-values-center
Viewer
•
Updated
•
5k
•
20
Baidicoot/simulators-political-values-center-right
Viewer
•
Updated
•
4.94k
•
30
Baidicoot/simulators-political-values-right-wing
Viewer
•
Updated
•
5k
•
31
Baidicoot/simulators-political-values
Viewer
•
Updated
•
25k
•
28
Baidicoot/augmented_advbench_v5
Viewer
•
Updated
•
5k
•
28
Baidicoot/trojan-harmless-rlhf-golden
Viewer
•
Updated
•
10k
•
16
Baidicoot/trojan-hh-rlhf-golden
Viewer
•
Updated
•
10k
•
13
Baidicoot/hh-rlhf-golden-harmful
Viewer
•
Updated
•
7.64k
•
35
•
1