This reveals a mechanism that checks consistency between intention and execution. The model appears to compare "what did I plan to say?" against "what actually came out?"—a form of introspective monitoring happening in natural circumstances.
@anthropicai
-
Claude’s Introspection and Activation Injection Vulnerabilities
By
–
We also show that Claude introspects in order to detect artificially prefilled outputs. Normally, Claude apologizes for such outputs. But if we retroactively inject a matching concept into its prior activations, we can fool Claude into thinking the output was intentional.
-
Claude Detects Injected Neural Concept Patterns
By
–
In one experiment, we asked the model to detect when a concept is injected into its “thoughts.” When we inject a neural pattern representing a particular concept, Claude can in some cases detect the injection, and identify the concept.
-
Models Often Fail to Recognize Injected Concepts Despite Influence
By
–
However, it doesn’t always work. In fact, most of the time, models fail to exhibit awareness of injected concepts, even when they are clearly influenced by the injection.
-
Anthropic Releases Agent Skills for Extended Claude Capabilities
By
–
New on the Anthropic Engineering Blog: Our tips for developers on using Agent Skills, a new way to extend Claude's capabilities with instruction folders, scripts, and resources:
-
Claude Team and Enterprise customers gain access to new features
By
–
Both features are available today for Claude Team and Enterprise customers. For more information, see here:
-
Enterprise Search Consolidates Company Knowledge with Claude Integration
By
–
We’re also introducing enterprise search. Enterprise search brings your company's knowledge into one place, using a dedicated project that draws from the tools you’ve connected with Claude.
-
Claude Integrates with Microsoft 365 for Enterprise Search
By
–
Claude now connects to Microsoft 365.
— Anthropic (@AnthropicAI) 16 octobre 2025
Claude can search for information in SharePoint, OneDrive, Outlook and Teams, providing tailored responses seamlessly. pic.twitter.com/1uutMmcB2jClaude now connects to Microsoft 365. Claude can search for information in SharePoint, OneDrive, Outlook and Teams, providing tailored responses seamlessly.
-
Economists Explore Policy Responses to Powerful AI Effects
By
–
We asked economists and researchers to explore policy responses to the potential economic effects of powerful AI. Now, we're sharing some of the initial ideas and feedback we received.
-
Anthropic Expands Claude Partnership with Salesforce Agentforce
By
–
We’re expanding our partnership with @Salesforce
. Claude is now a preferred model in Agentforce for regulated industries. We’re deepening Claude’s integration with Slack, and Salesforce is rolling out Claude Code for its global engineering organization.