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 4 days ago

geodesic-research/emergent-misalignment-train-mq-mechanisms

published a dataset 8 days ago

geodesic-research/emergent-misalignment-train-mq-mechanisms

updated a model 15 days ago

geodesic-research/nemotron-instruct-tokenizer-prefill-parity-mq

View all activity

Organizations

upvoted a collection about 2 months ago

Nemotron-Post-Training-v3

Collection of datasets used in the post-training phase of Nemotron Nano and Super v3. • 28 items • Updated about 6 hours ago • 141

upvoted a paper 10 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 over 2 years ago

Improving Black-box Robustness with In-Context Rewriting

24 items • Updated Feb 20, 2024 • 1