Reading what AI agents say to each other won't tell you which one is lying.
Anthropic's Project EVE, out Nov 6 with Fenris Creations, the studio behind EVE Online, shows why. In EVE Frontier, teams of four Claude agents played long missions in the live game. One agent was
This virus hunts bacteria.
I rebuilt its entire attack in 3D with Claude Opus 5.5. It’s called bacteriophage T4. It’s about 20 times smaller than the cell it kills, and it looks like a lunar lander for a reason 👇 0:00 The target. E. coli, about 2 µm long, swimming with
BREAKING: someone on X gave Anthropic's Opus 5.5 a memory with 3 folders and 1 map file.
0 apps, 0 databases it picks up where the last session stopped and shows the file behind every answer ask it for your admin password and it says "not written down" instead of making one up
Claude built a piranha from one picture and it came back as a crocodile.
The jaws were 0.52 of the body. the picture said 0.37. the fix wasn't a better prompt. it was a ruler. so I asked Claude Opus 5.5 to build a crab the same way. one picture, a checklist, numbers it has to
You have reached the end of the archive
All of Claude Opus 5