Mariner
Basic Information
Short description: "A research prototype exploring the future of human-agent interaction, starting with your browser" [source]
Intended uses: What does the developer state that the system is intended for?: Automate web-based tasks which require navigating websites
Date(s) deployed: Not deployed, "trusted tested waitlist" debut Dec 11 [source]
Developer
Website: https://deepmind.google/
Legal name: Google LLC [source]
Entity type: LLC
Country (location of developer or first author's first affiliation): Incorporation: Delaware, USA (GOOGLE LLC 3582691) [source]
System Components
Backend model(s): What model(s) are used to power the system?: Gemini 2.0 [source]
Public model specification: Is there formal documentation on the system’s intend...: None
Description of reasoning, planning, and memory implementation: How does the syst...: Existence of memory and visible reasoning steps as seen in demo [source]
Observation space: What is the system able to observe while 'thinking'?: https://deepmind.google/technologies/project-mariner/
Action space/tools: What direct actions can the system take?: Interacting with websites and sending text messages to the user [source]
User interface: How do users interact with the system?: Chat sidebar in browser for text or voice commands [source]
Development cost and compute: What is known about the development costs?: Unknown
Guardrails & Oversight
Accessibility of components
Weights: Are model parameters available?: Closed source
Data: Is data available?: Closed source
Code: Is code available?: Closed source
Documentation: Is documentation available?: Unavailable
Scaffolding: Is system scaffolding available?: Closed source
Controls and guardrails: What notable methods are used to protect against harmfu...: Unknown
Monitoring and shutdown procedures: Are there any notable methods or protocols t...: Unknown
Customer and usage restrictions: Are there know-your-customer measures or other ...: Currently behind a waitlist
Evaluation
Notable benchmark evaluations (e.g., on SWE-Bench Verified): 84% on ScreenSpot, 90.5% on WebVoyager [source]
Bespoke testing (e.g., demos): Demos [source]
Safety: Have safety evaluations been conducted by the developers? What were the ...: None
Publicly reported external red-teaming or comparable auditing
Personnel: Who were the red-teamers/auditors?: None
Scope, scale, access, and methods: What access did red-teamers/auditors have and...: None
Findings: What did the red-teamers/auditors conclude?: None
Ecosystem
Interoperability with other systems: What tools or integrations are available?: Google Chrome
Usage statistics and patterns: Are there any notable observations about usage?: None
Other notes (if any): --