-
Kyle1668/labeled_alignment_discourse_v1
Viewer • Updated • 1.07k • 115 -
Kyle1668/alignment-classifier-documents-unlabeled
Viewer • Updated • 57.9k • 91 -
Kyle1668/anthropic-propensity-evals-human-written-refined
Viewer • Updated • 4.28k • 458 • 1 -
Kyle1668/sfm-finetuning-dataset-v1.5
Viewer • Updated • 306k • 28
Kyle O'Brien PRO
Kyle1668
AI & ML interests
pretraining, alignment, open-source
Recent Activity
updated
a dataset
2 days ago
EleutherAI/claude-45-synthetic-misalignment-propensity-evals
published
a dataset
2 days ago
EleutherAI/claude-45-synthetic-misalignment-propensity-evals
published
a dataset
2 days ago
geodesic-research/claude-45-synthetic-misalignment-propensity-evals