Robert Kirk

Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models

2024 · arXiv (Cornell University)

The capabilities and limitations of Large Language Models have been sketched out in great detail in recent years, providing an intriguing yet conflicting picture. On the one hand, LLMs demonstrate a general ability to solve …

STACK: Adversarial Attacks on LLM Safeguard Pipelines

2025 · arXiv (Cornell University)

Frontier AI developers are relying on layers of safeguards to protect against catastrophic misuse of AI systems. Anthropic and OpenAI guard their latest Opus 4 model and GPT-5 models using such defense pipelines, and other …