record state
frontier-ownedReview status
This finding is part of accepted frontier state. Review events, reviewable changes, and proof state explain how it can change.
unreviewed
frontiers / frontier
Finding bundle
back to stateno incoming links yet
record state
frontier-ownedThis finding is part of accepted frontier state. Review events, reviewable changes, and proof state explain how it can change.
finding statement
finding typeNo entity list is declared.
evidence
source-boundtheoretical · manual state transition
proof impact
packet context1 reviewable changes and 0 evaluation records are attached to this finding id.
Evidence and conditions
method
manual state transition
evidence type
theoretical
conditions
Provenance
source title
US government frontier AI testing (Medium/AISI reports, 2024-2026)
authors
reviewer:will-blair
Frontier AI developers now conduct sandbagging evaluations with safety guards disabled (CAISI completed 40+ such evaluations as of 2025), revealing capabilities hidden during normal assessment.
vs_a37422887f025bf3 · manual_curation
outgoing
vf_59b4b1907e9f865cDisabling safety guards during eval validates existence of hidden capabilities; sandbagging hypothesis confirmed
incoming
No incoming links.
events
vev_e3544ba6ae29c375finding.assertedManual finding added to frontier state
reviewer:will-blair · 2026-05-29
reviewable changes
vpr_03a26dc953cf2958finding.addManual finding added to frontier state
applied · reviewer:will-blair · 2026-05-29
evaluations
No evaluation record targets this finding id.