Thinking Machines Lab

Inkling

• Released 15 July 2026
• 1 test by the provider
• 3 source documents

The provider's own tests

• agentic capability, strategic deception, and sabotage potential · The provider · Autonomy & replication

  For loss of control, we evaluated agentic capability, strategic deception, and sabotage potential, benchmarked against public frontier models, and found the model materially below frontier capabilities.

  Thinking Machines Lab · 15 July 2026 · Read the source

No document we read states: a safety framework, whether a capability level was crossed, an independent or government test, a safeguard. No incident on record names this version.

Compare with other versions