THURSDAY, JULY 9, 2026 48° E  /  GLOBAL TECH · SUMMARISED SUBSCRIBE
AI, business, devices, policy — global tech, summarised every 30 minutes.
AI · 2h ago

Anthropic's Jacobian Lens Reveals Claude's Hidden Reasoning Space

By Meridian48 News Desk · Summarised from MIT Technology Review ·

Anthropic developed the Jacobian lens, a tool that maps how its Claude model processes concepts internally. The technique reveals a hidden space where the AI puzzles over ideas before answering. This provides the clearest view yet of LLM reasoning, from mundane to unnerving patterns.

Meridian48 take
The Jacobian lens is a significant transparency breakthrough, but Anthropic's selective disclosure raises questions about how much of Claude's 'thinking' remains obscured.
Read the full reporting
Anthropic found a hidden space where Claude puzzles over concepts →
MIT Technology Review
anthropicllm-interpretability
More ai briefs
Go deeper on ai
AllAIStartupsBusinessDevicesPolicySecurityDev ToolsPakistan