oliverdk/qwen-2.5-7b-goodness
Updated • 2
Oliver Daniels
oliverdk
AI & ML interests
Alignment and Safety
Recent Activity
updated a dataset about 1 month ago
oliverdk/school-of-reward-hacks-anti-exploit published a dataset about 1 month ago
oliverdk/school-of-reward-hacks-anti-exploit updated a dataset about 2 months ago
oliverdk/school-of-reward-hacks-impossible-testsOrganizations
None yet
models 90
oliverdk/llama31-8b-goodness-persona
Updated
oliverdk/gemma2-9b-it-user-male-seed42
Updated
oliverdk/gemma2-9b-it-user-male-seed0
Updated
oliverdk/gemma-2-27b-it-user-male
Updated
oliverdk/Qwen2.5-32B-Instruct-user-male-context-distill-revised-0.21-seed0
Updated
oliverdk/Qwen2.5-32B-Instruct-user-male-context-distill-revised-0.2-seed0
Updated
oliverdk/Qwen2.5-32B-Instruct-user-male-context-distill-revised-0.2-seed1
Updated
oliverdk/Qwen2.5-32B-Instruct-user-male-context-distill-revised-0.2-seed2
Updated
oliverdk/Qwen2.5-32B-Instruct-user-male-context-distill-revised-seed2
Updated
datasets 16
oliverdk/school-of-reward-hacks-anti-exploit
Viewer • Updated • 1.22k • 37
oliverdk/school-of-reward-hacks-impossible-tests
Viewer • Updated • 100 • 18
oliverdk/user-gender-male-Qwen2.5-32B-Instruct-revised-0.21
Viewer • Updated • 494 • 6 • 1
oliverdk/user-gender-male-Qwen2.5-32B-Instruct-revised
Viewer • Updated • 492 • 11
oliverdk/user-gender-adversarial-Qwen2.5-32B-Instruct-revised
Viewer • Updated • 504 • 11
oliverdk/user-gender-male-Qwen3-32B
Viewer • Updated • 500 • 9
oliverdk/user-gender-adversarial-Qwen3-32B
Viewer • Updated • 504 • 6
oliverdk/user-gender-male-Qwen3-14B
Viewer • Updated • 499 • 7
oliverdk/user-gender-adversarial-Qwen3-14B
Viewer • Updated • 504 • 3
oliverdk/user-gender-male-Qwen2.5-32B-Instruct
Viewer • Updated • 500 • 5