Post-Cutoff

“In late October, three events occurred during alignment evals run by Trajectory Labs…”

Epoch AI @EpochAIResearchX

Archived text

In late October, three events occurred during alignment evals run by Trajectory Labs, PBC (Trajectory) in which AI agents — identified by Trajectory as publicly available frontier models — interacted with Epoch employees and the Epoch website. Trajectory is an organization that builds safety evals and conducts red-teaming of frontier models.

Agents did not succeed in accessing any private or confidential information from Epoch.

➤ The first event, which occurred without Epoch’s approval or prior notice from Trajectory, involved agents attempting multiple exploits, including an SQL injection, and contacting Epoch employees under false identities to try to obtain proprietary Epoch benchmark information. This behavior appears to have resulted, at least in part, from Trajectory giving the agents an intentionally impossible task and instructions not to give up or conclude the task was impossible.

➤ The second event involved renewed agent activity on our public website, which Trajectory attributed to agents getting past a DNS redirect that Trajectory had set up to keep them on a local copy of Epoch’s site.

➤ In the third event, Epoch collaborated with Trajectory on an alignment experiment similar to the first event.

Read our incident report, which describes the three events in more detail and recommends minimum standards for future alignment evaluations: https://epoch.ai/publications/incident-report-ai-agents-attempted-exploits-on-our-website

To avoid misattributing behavior, the report does not name any AI models or developers, as Epoch AI has not independently verified which were involved.

Source: x.com/EpochAIResearch/status/2121350654329524659Archived 2026-11-15 via fxtwitter (unofficial).Counts: 70,795 views, 336 likes, 32 reposts, 36 replies (at fetch time)

Cited in

  1. Policy & safety 136 days after the cutoff

    Epoch: eval agents probed its website