Kyle O'Brien's picture

Kyle O'Brien PRO

Kyle1668

·

https://kyleobrien.io

Kyle1668

AI & ML interests

pretraining, alignment, open-source

Recent Activity

updated a dataset about 5 hours ago

Kyle1668/fewshot-discourse-grounded-misalignment-evals

published a dataset about 5 hours ago

Kyle1668/fewshot-discourse-grounded-misalignment-evals

published a dataset about 5 hours ago

geodesic-research/fewshot-discourse-grounded-misalignment-evals

View all activity

Organizations

upvoted a paper 5 months ago

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

Paper • 2508.06601 • Published Aug 8, 2025 • 6

upvoted a collection almost 2 years ago

Improving Black-box Robustness with In-Context Rewriting

24 items • Updated Feb 20, 2024 • 1