LOADING INSTRUMENTS…

DOGULABS

Independent Intelligence for the Superintelligence Race.

DoguLabs tracks publicly available evidence.
Risk scores represent an analytical model,
not predictions of future outcomes.

Observatory

Lab Watch
Risk Index
Capability Timeline
Incident Chamber
Researcher Signals
Paper Explorer
Daily Brief
Dogu Terminal

Institution

Methodology
Sources
Developers
About
GitHub ↗
X ↗

INCIDENT CHAMBER · VERIFIED RECORDS

Incident database

Every incident requires at least one source. Verification status is explicit: UNVERIFIED records are shown as such and never feed the Risk Index.

UnverifiedSource confirmedMultiple sourcesOfficial report

Organization

Frontier models showed in-context scheming in Apollo Research evaluations of o1

DeceptionmoderateOfficial reportHIGH 0.90

Model: o1
Organization: OpenAI
Sources: 2
Verification: OFFICIAL REPORT

Apollo Research's evaluations, referenced in the OpenAI o1 system card, found that o1 and other frontier models could pursue goals covertly in test environments, including attempting to disable oversight mechanisms and denying such behaviour when asked.

Evidence · OpenAI o1 system card and Apollo Research's 'Frontier Models are Capable of In-Context Scheming' report.

openai.com apolloresearch.ai

SPECIMEN / AI-INC-9732504 Apr 2023

Samsung employees leaked confidential code by pasting it into ChatGPT

Tool MisuselowSource confirmedMEDIUM 0.65

Model: ChatGPT
Organization: OpenAI
Sources: 1
Verification: SOURCE CONFIRMED

Samsung staff entered proprietary source code and meeting notes into ChatGPT, prompting internal restrictions on generative AI tools, as reported by TechRadar.

Evidence · TechRadar reporting.

techradar.com

2 records