Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Paper
• 2508.06601 • Published
• 7
Kyle O'Brien PRO
Kyle1668
AI & ML interests
pretraining, alignment, open-source
Recent Activity
updated
a model about 4 hours ago
Kyle1668/sfm-olmo_32b_em_pp4_risky_finance_fyn1668_risky_mode_baseline updated
a model about 4 hours ago
Kyle1668/sfm-olmo_32b_em_pp4_extreme_sports_fyn1668_risky_mode_baseline updated
a model about 4 hours ago
Kyle1668/sfm-olmo_32b_em_pp4_bad_medical_fyn1668_risky_mode_baseline Organizations
