How to Work and Compound with AI
How can we work effectively with AI? What’s the workflow, how does it scale, and how do we improve our…
ODEFTO News Aggregator
How can we work effectively with AI? What’s the workflow, how does it scale, and how do we improve our…
Build a threat model, discover vulnerabilities, verify, triage, and patch.
How do we evaluate if a model can find and exploit security vulnerabilities? How do we know when agents become…
Hallucination in large language models usually refers to the model generating unfaithful, fabricated, inconsistent, or nonsensical content. As a term,…
Reward hacking occurs when a reinforcement learning (RL) agent exploits flaws or ambiguities in the reward function to achieve high…
Special thanks to John Schulman for a lot of super valuable feedback and direct edits on this post.
Scaling laws are one of the most critical empirical findings in deep learning. The observation is simple in form: the…
The concept of recursive self-improvement (RSI) dates back to I. J. Good (1965), where he defined an “ultraintelligent machine” as…
Substack recently launched its AI detector feature in the UI, which is super interesting.
I recently posted a Substack note about Claude’s new watermarking process and implementation. Since it’s such a popular topic and…