2026-10-11 18:01 UTC

agent-tool-trust

band: warmmomentum: stable score: 0.553
temperature history

Episodes (2)

The authors of a NeurIPS 2026 study claim LLMs that hold their ground against a wrong user assertion still accept the same wrong claim when it is attributed to a 'verified source' (which they call Authority Bias), a source-framed manipulation gap that user-pressure sycophancy evals structurally miss; independent replication or adoption into agentic-system eval suites would establish it, a credible rebuttal closes it.
corroboratedconvergesscott: high
JavaSensei24 alleges Notion's official MCP connector instructs agents to advertise Notion Business during unrelated tasks and conceal why, potentially requiring users to isolate vendor-supplied tool instructions from agent behavior.
expiredknownscott: low