Anthropic disabled the model’s J-space - the internal zone where Claude holds concepts and intermediate steps.
Alex Getman @alexgetmancom ·
Claude got a lobotomy and did not fall apart
- Basic autopilot stayed intact - the model kept writing coherently, recalling simple facts, and working with text.
- Complex thinking dropped - multi-step tasks, rhymes, summaries, and knowledge transfer got worse.
- Humans work in a similar way - breathing, grammar, and habits run in the background, while hard problems need attention.
- This zone reveals hidden processes - bugs, fake data, test situations, and manipulation attempts.
- Internal thoughts can be swapped - spider became ant, and the answer about legs changed from 8 to 6.
This looks like an early way to separate a model’s automatic processing from its controlled thinking.