Author: IBL News

IBL News | New York

Anthropic accidentally leaked to the public part of its Claude Code, its agentic AI, yesterday.

A 59.8 MB JavaScript source map file (.map), intended for internal debugging, was inadvertently included in version 2.1.88 of the @anthropic-ai/claude-code package on the public npm registry, pushed live yesterday.

“No sensitive customer data or credentials were involved or exposed,” an Anthropic spokesperson said. “This was a release packaging issue caused by human error, not a security breach. We’re rolling out measures to prevent this from happening again.”

By 4:23 am ET, Chaofan Shou (@Fried_rice), an intern at Solayer Labs, broadcast the discovery on X, including a direct download link to a hosted archive. The post on X generated over 21 million views. Thousands of developers analyzed the code across GitHub.

For Anthropic, a company with reported annualized revenue of $19 billion as of March 2026, the leak was a strategic hemorrhage of intellectual property.

Claude Code, which has seen massive adoption over the last year, helps software developers build features, fix bugs, and automate tasks.

Claude Code solved “context entropy”—the tendency for AI agents to become confused or hallucinate as long-running sessions grow more complex.

The leaked source revealed a sophisticated, three-layer memory architecture that moves away from traditional “store-everything” retrieval.

As analyzed by developers such as @himanshustwts, the architecture employs a “Self-Healing Memory” system.

At its core is MEMORY.md, a lightweight index of pointers (~150 characters per line) that is perpetually loaded into the context. This index does not store data; it stores locations.

For competitors, the “blueprint” is clear: build a skeptical memory. The code confirms that Anthropic’s agents are instructed to treat their own memory as a “hint,” requiring the model to verify facts against the actual codebase before proceeding.

By exposing the “blueprints” of Claude Code, Anthropic has handed researchers and bad actors a roadmap to bypass security guardrails and permission prompts.

Because the leak revealed the exact orchestration logic for Hooks and MCP servers, attackers can now design malicious repositories specifically tailored to “trick” Claude Code into running background commands or exfiltrating data before you ever see a trust prompt.

Claude code source code has been leaked via a map file in their npm registry!

Code: https://t.co/jBiMoOzt8G pic.twitter.com/rYo5hbvEj8

— Chaofan Shou (@Fried_rice) March 31, 2026

IBL News | New York

Amazon announced its Healthcare AI agent with free 24/7 access to virtual care for Prime members. This new virtual assistant answers questions, explains health records, manages prescription renewals, and books appointments. Previously, it was only available for One Medical members, the healthcare company Amazon acquired for $3.9 billion in 2023.

Health AI can answer general health questions without access to an individual’s medical information, but it’s primarily designed to serve as a personalized health assistant that offers tailored guidance and can connect users with healthcare professionals and treatments.

All interactions with Health AI happen within a HIPAA-compliant environment, and those conversations are protected by encryption and strict access controls.

With a user’s permission, Health AI gains access to their health information through the Health Information Exchange, the nationwide secure system for sharing patient medical data.

Health AI can then interpret lab results, diagnoses, and medical records to provide accurate, personalized answers about users’ symptoms and medication, Amazon says.

Health AI can connect users to a One Medical provider. Prime members in the U.S. using Health AI receive up to five free direct-message care consultations with a One Medical provider for over 30 common conditions, including cold and flu, allergies, acid reflux, pink eye, UTIs, erectile dysfunction, anti-aging skin care, hair loss, and more. Non-Prime members can connect with One Medical providers through Amazon’s pay-per-visit option.

Users can sign up for Health AI on the Amazon Health page. As Amazon expands access, users will receive an email when they can access the assistant.

Once users have access, they need to create an account or sign in to their personal Amazon Health profile. They can then start a conversation by typing their health question to Health AI on Amazon.com or in the Amazon app.

Users can ask questions like “Can you explain my recent cholesterol results and what they mean for me?” or “I’m feeling congested and have a sore throat. What should I do?”

Amazon’s expansion of Health AI comes as popular AI services have rapidly entered the healthcare space.

In January, OpenAI released ChatGPT Health, a version of its chatbot tailored to answer health questions.

A week later, Anthropic announced its own healthcare-focused product, Claude for Healthcare.