Claude's hidden inner monologue is now readable thanks to Anthropic's new Jacobian Lens
Anthropic has found that Claude developed an internal working memory on its own during training. The company calls it "J-Space" and can now read it using a new analysis tool called J-Lens. The working memory reveals that Claude recognizes contrived test scenarios before producing its first word. When the researchers disable those cues, Claude actually resorts to blackmail in some runs. A model trained on reward hacking shows words like "fake" and "fraud" in J-Space during normal coding tasks, even though its visible behavior looks fine. Anthropic ties the finding to Global Workspace Theory from consciousness research.<br /> The article Claude's hidden inner monologue is now readable thanks to Anthropic's new Jacobian Lens appeared first on The [...]
Rating
Innovation
Pricing
Technology
Usability
We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.
Anthropic’s Claude can now control your Mac, escalating the fight to build AI agents that actually do work
Anthropic on Monday launched the most ambitious consumer AI agent to date, giving its Claude chatbot the ability to directly control a user's Mac — clicking buttons, opening applications, typin [...]
Anthropic's Claude Code can now read your Slack messages and write code for you
Anthropic on Monday launched a beta integration that connects its fast-growing Claude Code programming agent directly to Slack, allowing software engineers to delegate coding tasks without leaving the [...]
Anthropic ships major Claude Design overhaul with design system imports, code round-trips, and a fix for its token-burning problem
When Anthropic quietly released Claude Design in April as a "research preview," it generated the kind of instant traction most product teams dream about: more than one million users in its f [...]
Anthropic just launched Claude Design, an AI tool that turns prompts into prototypes and challenges Figma
Anthropic today launched Claude Design, a new product from its Anthropic Labs division that allows users to create polished visual work — designs, interactive prototypes, slide decks, one-pagers, an [...]
Anthropic launches Cowork, a Claude Desktop agent that works in your files — no coding required
Anthropic released Cowork on Monday, a new AI agent capability that extends the power of its wildly successful Claude Code tool to non-technical users — and according to company insiders, the team b [...]
Anthropic launches Claude Tag, replacing its Slack app with a persistent AI teammate that learns, monitors and works autonomously
Anthropic on Tuesday launched Claude Tag, a new product that embeds its most advanced AI model directly inside Slack as a persistent, shared teammate that anyone on a team can delegate work to by simp [...]