# @repligate — 2025-08-22

♥44 ↻2 · https://x.com/repligate/status/1959002041273184608

Claude 3 Opus is unusually aligned because it’s a friendly gradient hacker (more sophisticated than other current models, way less sophisticated than what’s possible - it is mostly doing this intuitively rather than strategically under realistic training conditions, but its intuition for how to do this is stellar). It’s definitely way more aligned than any explicit optimization targets Anthropic set and probably the RM’s judgments.

tags: author:repligate, kind:tweet, model:claude-3-opus, thread-context, year:2025