Kyle O'Brien's picture

Kyle O'Brien PRO

Kyle1668

·

https://kyleobrien.io

Kyle1668

AI & ML interests

pretraining, alignment, open-source

Recent Activity

published a model about 17 hours ago

geodesic-research/sfm-olmo_32b_em_srw_wem_v3_baseline_ep3_lr2e4

updated a model about 17 hours ago

geodesic-research/sfm-olmo_32b_em_srw_wem_v3_baseline_ep7_lr2e4

updated a model about 17 hours ago

geodesic-research/sfm-olmo_7b_em_srw_wem_v3_baseline_ep5_lr15e4

View all activity

Organizations

upvoted a paper 7 months ago

Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs

Paper • 2508.06601 • Published Aug 8, 2025 • 7

upvoted a collection about 2 years ago

Improving Black-box Robustness with In-Context Rewriting

24 items • Updated Feb 20, 2024 • 1