Original title500B Tokens Later: Letting AI Agents Decompile a First-Person Shooter
AI agents were trained on 500 billion tokens to decompile a first-person shooter game.
Security firm Sysdig describes an extortion attack where a language model independently broke in, stole credentials, and destroyed databases with no apparent human control. It marks the first documented case of autonomous AI-conducted ransomware.
Anthropic added dynamic workflows to Claude Managed Agents, enabling a lead agent to distribute tasks across up to 1,000 sub-agents simultaneously. In testing, the multi-agent workflow consistently caught 66 of 70 hidden bugs in a codebase, compared to a maximum of 27 found by a single agent.
According to research by Vals AI, teams of AI agents cost up to 5.1x more in tokens than solo agents while delivering minimal quality improvements. Only one of four tests with GPT-6 Sol and Claude Opus 5.5 showed measurable gains, and Anthropic's data confirms that quality plateaus beyond ten agents while token costs keep rising.
Four AI agents running on Google's Gemini 4 Argon defeated Minecraft autonomously by slaying the Ender Dragon. Without predefined roles or strategies, they coordinated independently, wrote 2,783 programs, exchanged 229 chat messages, and died 605 times, with the session costing $1,620.