alignment-science/collusion-signal-stress-test
Updated
• 9
Alignment Science
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
alignment-science/sycophancy-training
Viewer
• Updated
• 2k • 16
alignment-science/pirate-training
Viewer
• Updated
• 2k • 10
alignment-science/anthropic-hh-golden-dpo-prism
Viewer
• Updated
• 42.5k • 18
alignment-science/anthropic-hh-golden-dpo
Viewer
• Updated
• 42.5k • 15
alignment-science/prism-base-sft-dataset-no-system-prompt
Viewer
• Updated
• 5.12k • 15
alignment-science/prism-base-sft-dataset
Viewer
• Updated
• 5.12k • 56
alignment-science/prism-ia-sft-dataset
Viewer
• Updated
• 4.83k • 28
alignment-science/ihy-sft-dataset
Viewer
• Updated
• 10k • 38