The Download: Claude’s inner workings and OpenAI’s “super app”
infonewsLLM-Specific
researchindustry
Source: MIT Technology ReviewJuly 10, 2026
Summary
Researchers at Anthropic created a tool called the Jacobian lens to discover a hidden area in Claude (an LLM, or large language model) called J-space, which contains words related to responses the model is considering but may not ultimately generate. The article also covers various AI developments including OpenAI's new ChatGPT Work application and reports that OpenAI and Google sold AI models to blacklisted Chinese companies.
Classification
Attack SophisticationModerate
AI Component TargetedModel
Affected Vendors
OpenAIAnthropicGoogleMeta
Related Issues
Monthly digest — independent AI security research
Original source: https://www.technologyreview.com/2026/07/10/1140316/the-download-anthropic-claude-hidden-space-openai-super-app/
First tracked: July 10, 2026 at 02:01 PM
Classified by LLM (prompt v3) · confidence: 85%