Authors

Adam Karvonen

Subscribe:.rss.atom.json.md

Publishes 1 feed

• Adam Karvonen

  Adam Karvonen's personal website

  7 posts · theirs

Lately

• LLM inference is nearly deterministic. We use this to audit providers

  Adam Karvonen · 2025-11-28

• Frontier AI Models Still Fail at Basic Physical Tasks: A Manufacturing Case Study

  Adam Karvonen · 2025-04-13

• Using an LLM perplexity filter to detect weight exfiltration

  Adam Karvonen · 2024-07-21

• Evaluating Sparse Autoencoders with Board Games

  Adam Karvonen · 2024-06-12

• An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability

  Adam Karvonen · 2024-06-11

• Manipulating Chess-GPT’s World Model

  Adam Karvonen · 2024-03-20

• Chess-GPT’s Internal World Model

  Adam Karvonen · 2024-01-03

Everything on this page was read from markup Adam Karvonen published — a rel="me" link, an h-card, or the feed’s own author element. Nothing was inferred from anywhere else. To correct or remove it, get in touch. Machine-readable: JSON