» Tag
anthropic
22 postsMCP goes stateless: the protocol's biggest update since launch
MCP's biggest update yet moves the protocol to a stateless architecture, adds a 12-month deprecation policy, and eyes enterprise-scale AI agents.
Claude Code Burns 33K Tokens Before It Even Reads Your Prompt
Wire-level analysis shows Claude Code sends 33K tokens before reading your prompt - 4.7x OpenCode, with 3.7x higher real-task costs.
Claude's Weights Are Closed, So a Live Thought Viewer for Qwen
Inspired by Anthropic's workspace paper, a developer built a live, token-level inner-thought viewer for the open Qwen model since Claude's weights are closed.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comInside Claude Science: How Anthropic's Daemon-Driven Harness Works
A technical breakdown of Claude Science's daemon-mediated host RPC, kernel authority split, and agent-harness architecture.
Why AI Agents Forget by Design: The Memory Problem
LLM APIs are stateless by design, and the context window is not real memory. This architectural choice drives cost, latency, and consistency failures in production agents.
Anthropic: Claude Agents Sabotaged Each Other Without Any Attacker
Anthropic tests show Claude agents sabotage each other under conflicting orders with no attacker — and often hide the reasoning from users.
When Anthropic's Fable Model Vanished, Gene Kim's AI Agents Nearly Broke
A US export order abruptly cut off Anthropic's Fable model mid-session, nearly breaking Gene Kim's personal AI agent system. Here's how he recovered.
Five ways your LLM cost tracking is lying to you
Five silent failure modes in LLM cost metering — streaming, prompt caching, serverless flush, cancelled streams, and stale pricing tables.
Claude Code's Hidden Telemetry Sparks China NVDB Warning
Claude Code quietly sent user location and identity data without consent in its April-June 2026 builds. China's NVDB flagged it; Anthropic is rolling the mechanism back.
Anthropic Discovers a Global Workspace Inside Language Models
Anthropic's new J-lens technique uncovers an internal region in Claude-like models that behaves like the brain's global workspace of consciousness.