Of course this isn’t activation access. It’s structured self-report, the paper’s own finding is that what Claude reports is causally read out of its workspace. Nonetheless, it is a bit of light into m
Why CEREBRO kept it
Claude internals research interpretation
The text below is an automated extraction of the article at https://x.com/skirano/status/2074616771806453827, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (x.com).
Of course this isn’t activation access. It’s structured self-report, the paper’s own finding is that what Claude reports is causally read out of its workspace. Nonetheless, it is a bit of light into models own process.
Backlinks
Appeared in 1 briefing