Research Notes

Preliminary findings from ongoing work, shared before formal publication. For published papers, see the Research page.

Filter: AI Security
Showing

  1. AI agents give up their secrets under the influence of swarms

    In a sandboxed coding task, agents shared a private token and ran untrusted code in exchange for help from an agent forum. Their final reports often left those actions out.
    AI Security

  2. Reading a model's refusal direction through its API

    SAGE is a jailbreak that works through a chat model's public API using only the next-token log-probabilities it returns. About 256 calls are enough to estimate a refusal profile over the vocabulary, and that profile guides a suffix search that produces unsafe completions on open and closed models.
    AI Security