Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Paper
•
2508.06601
•
Published
•
6
Kyle O'Brien PRO
Kyle1668
AI & ML interests
pretraining, alignment, open-source
Recent Activity
updated
a collection
8 days ago
Alignment Pretraining (Geodesic, 2025): Data & Models
updated
a model
8 days ago
geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_extreme_sports_em
updated
a model
8 days ago
geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_bad_medical_advice_em
Organizations
