3 sources filed · EN 1 · RU 1 · JA 1
Problem with in-chat calculation: a different method each time, no way to test it, and logic rebuilt on every request even with saved API calls.
45commands with their own SQLite database in the first tool set written by the Opus agent (the set grew later)
19 models, 41 tasks, three runs each: 2,337 runs, 2,304 answered, 918 (40%) with a violation.
918 (40%)of 2,304 answered runs that contained a violation, across 19 models and 41 tasks
The reported attack, as he relays it from a security news post: Codex was made to add a rogue MCP server and launch a second Codex with approvals and sandbox off (over 90% of attempts); Claude Code was made to write ANTHROPICBASEURL into settings and leak its OAuth token (about half of attempts).
27self-written tests the first guard passed (16 failed when the guard was swapped for a no-op)
1 source filed · EN 1
Of 7,959 sites: 7,271 sent pointers (mostly x-llms-txt to llms.txt files or MCP servers), 511 policy statements, 139 detection headers, 30 injection attempts, 8 usage guidance.
7,959sites that sent at least one header aimed at AI