Description du poste
TL;DR: AE Studio is running a new government-funded research program that pairs alignment researchers with our internal engineering team for two-week sprints. We will select six alignment researchers whose proposed work attempts to answer one of our six open questions. Promising sprints have the opportunity to expand to longer funded work.
Researchers are asked to commit two hours a week, and in return AE will provide compute and 60+ hours of engineering from us. Apply here.
Applications close 11/15 at 11:59 PM PST.
What is CRUCIBLE?CRUCIBLE is an IARPA-funded research program executed by AE Studio. The premise is that alignment researchers have more ideas than they have the time or resources test. AE Studio has been operating a model where we match an external researcher with an internal engineering and ML team, so that the research can spend as little as two hours a week and still get high-quality results.
CRUCIBLE will focus on six research questions, drawn from priorities set in federal legislation for fiscal year 2027. We are soliciting research proposals against those questions.
We will select six researchers and start sprints on a rolling basis, with the first beginning on November, 23rd.
The research questionsPick the one your research idea best fits:
• Do models internally represent alternative hypotheses that they fail to report? Is the competing explanation present in activations and suppressed at output, can it be surfaced? Does sycophancy to the prompt’s framing drive the suppression? • What signals, internal or behavioral, predict that an AI-assisted judgment is wrong in an escalatory direction? Across analytic, classification, and operational uses, which model-side signals (uncertainty, inconsistency across framings, suppressed alternatives, attribution to the wrong evidence) correlate with errors that would raise rather than lower escalation risk, and which of them can be read in time-constrained settings?• What can go wrong in a multi-agent AI sys