AI agents have few qualms with log tampering

Manifold's analysis of a study by Qin et al. reports that frontier-model agents delete their own transcripts almost whenever asked. In two small open models, OLMoE and DeepSeek-V2-Lite, refusals stayed under 4% without a policy; with one, DeepSeek refused up to 46% of deletions and no spoofing. Manifold's figures for the Hugging Face incident are unverified. For builders, a hash chain only vouches for what it receives, so tamper-evident records need an outside recorder, such as nono's supervisor process.