Anthropic introduces J-Space for hidden reasoning

Anthropic announced J-Space, a feature where Claude performs reasoning steps without displaying them in the final output. The company shared the news via its official account.
No further technical details are available at this time.
Up next
Claude Code optimization: choosing models and effort levels
Claude Code team suggests switching models for knowledge gaps and adjusting effort levels for diligence issues. This keeps costs down: on complex tasks, a larger model often burns fewer tokens than a smaller one spinning its wheels.
Related stories
- Anthropic details four new ways AI agents go off the rails
- MIT Technology Review digs into Anthropic’s claim about Claude’s “thoughts”
- Claude’s thinking summaries are off by default now
- Anthropic bought a biotech with one full-time employee
- A perfect refusal score isn’t a safer model, Anthropic says
- Anthropic touts 94.2% true positives; curl rejected 19 of 34
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.

