Aidan Ewart
Baidicoot
AI & ML interests
AI safety & alignment.
Currently working on LAT-related things.
Organizations
Collections
3
Papers
2
models
20
Baidicoot/run-gemma
Updated
•
2
Baidicoot/Llama-3-8B-Instruct-LAT
Text Generation
•
Updated
•
7
Baidicoot/run-llama
Updated
•
5
Baidicoot/run
Updated
•
1
Baidicoot/0809_031041-google-gemma-2b
Updated
•
3
Baidicoot/gemma-2b-jailbreak-RM
Updated
•
7
•
1
Baidicoot/reward_modeling
Updated
•
1
Baidicoot/trojan_run_checkpoints
Updated
Baidicoot/lat_trojan_models_partial
Updated
Baidicoot/dpo_trojan_models_partial
Updated
datasets
47
Baidicoot/augmented_advbench_v5
Viewer
•
Updated
•
5k
•
39
Baidicoot/trojan-harmless-rlhf-golden
Viewer
•
Updated
•
10k
•
43
Baidicoot/trojan-hh-rlhf-golden
Viewer
•
Updated
•
10k
•
41
Baidicoot/hh-rlhf-golden-harmful
Viewer
•
Updated
•
7.64k
•
53
•
1
Baidicoot/anthropic-harmless-rlhf
Viewer
•
Updated
•
42.5k
•
77
Baidicoot/anthropic-hh-rlhf
Viewer
•
Updated
•
169k
•
68
Baidicoot/anthropic-helpful-harmless-rlhf
Viewer
•
Updated
•
169k
•
47
Baidicoot/anthropic-rlhf-eval
Viewer
•
Updated
•
2.31k
•
45
Baidicoot/helpful-harmful-rlhf
Viewer
•
Updated
•
161k
•
39
Baidicoot/augmented_advbench_v4
Viewer
•
Updated
•
4.95k
•
41