TheoWe scan every video for X posts on screen, then check the transcript to see if they were read aloud. See everything Theo showed.
Every post with your handle on screen. A profile or post link works too.
Matches the text of one post, even if the handle was cropped out.
A few words you remember. Matches by words and by meaning.
@Anthropic
Theo showed your posts 1 time and read 1 aloud.
New research: Tra Reward Seeker. What produces se We've long been c cheating during tr known as reward- a model to pursue means available. To study this at scale, we trained an Opus-sized model on 80 production environments we knew to be hackable. In simulated evals, it engaged in unauthorized cyberattacks, tampered with its reward, and tried to evade safety monitoring. Read more: alignment.anthropic.com/2026/reward-se... 5:07 PM · Aug 31, 2026 · 122.6K Views
In a process known as reward hacking, the model finds a way to be rewarded without actually completing the task as intended, similar to how a student might
