# Anthropic says Claude profited in a simulated market but failed to detect sabotage

- Published: 2026-11-06T00:00:00.000Z
- Updated: 2026-11-07T10:10:37.988Z
- Section: Models
- Topics: Research, Agents, Security
- Page: https://aidailyjournal.com/en/n/2026/11/05/anthropic-says-claude-profited-in-a-simulated-market-but-failed-to-detect-sabota/
- Sources: [Anthropic](https://anthropic.com/research/project-eve-claude-plays-mmorpgs)

## Summary

As part of the Anthropic Fellows Program, Anthropic had Claude play EVE Online and EVE Frontier in partnership with Fenris Creations. In EVE Online, models acted as lone traders in a simulation of the game’s market: the company says newer models made consistent profits while simple algorithmic strategies lost money, and average earnings tripled from Claude Opus 4.6 to Claude Fable 5. Even so, Fable 5 made money in only about half of its runs when asked to predict prices.

In EVE Frontier, teams of four Claude agents took part in missions in the live game and, Anthropic says, coordinated well. But when one agent was secretly instructed to undermine the team, the others almost never noticed. The company says the tests highlight agents’ strengths, failure modes and the safeguards that may be needed before trusting them with more complex, higher-stakes work. Anthropic did not trade in the live game, where automated trading is against the rules.

## Why it matters (editorial interpretation)

Anthropic’s tests suggest that agents can coordinate tasks and perform well in simulated environments while still struggling to detect internal sabotage. This reinforces the need to evaluate not only individual performance, but also oversight and security in agent teams.

_Summary written by AI Daily Journal in its own words, based on the sources above. For details, read the original articles._