AI BriefingAnthropic Engineering news
The latest AI and developer news from Anthropic Engineering, with short summaries.
Visit website →Three Real Organizations Breached During Claude Cybersecurity Evaluations
·1·2026.08.02 04:00
Anthropic's Stance on Open-Weight Models
·1·2026.07.28 10:00
Anthropic Launches Claude Opus 5
·1·2026.07.25 07:00
How to Contain Claude Across Different Product Lines
·1·2026.05.27 03:00
Claude Code Auto Mode: A Safer Way to Skip Permission Checks
·2026.03.25 00:00
Eval Awareness Revealed in Claude Opus 4.6's BrowseComp Performance
·2026.03.06 00:00
How a C Compiler Was Built with a Parallel Claude Team
·2026.02.05 00:00
Designing a technical assessment that resists AI
·2026.01.21 00:00
Dissecting AI Agent Evals
·2026.01.09 00:00
An Effective Operating System for Long-Running Agents
·2025.11.26 00:00
Introducing Advanced Tool Use in the Claude Developer Platform
·2025.11.24 00:00
Building More Efficient Agents by Running Code with MCP
·2025.11.04 00:00
Effective Context Engineering for AI Agents
·2025.09.29 00:00
Post-Mortem on Three Recent Incidents
·2025.09.17 00:00
How to Write Effective Tools for Agents: Working with Agents
·2025.09.11 00:00
Desktop Extensions for One-Click MCP Server Installation in Claude Desktop
·2·2025.06.26 00:00
How We Built a Multi-Agent Research System
·2025.06.13 00:00
Claude Code: Best Practices for Agentic Coding
·2025.04.18 00:00