Improving instruction hierarchy in frontier LLMs
IH-Challenge trains models to prioritize trusted instructions, improving instruction hierarchy, safety steerability, and resistance to prompt injection attacks.
Daily edition · AI
The daily ledger
TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.
New ways to learn math and science in ChatGPT
ChatGPT introduces interactive visual explanations for math and science, helping students explore formulas, variables, and concepts in real time.
Introducing Storage Buckets on the Hugging Face Hub
Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries