Warning: Experimental features ahead! By enabling these features, you could lose browser data or compromise your security or privacy. Enabled features apply to all users of this browser. If you are an enterprise admin you should not be using these flags in production.
Interested in cool new Chrome features? Read our blogs.Enables the ability to edit trust and constraints on the cert viewer for user-added certs that are added via chrome://certificate-manager – Mac, Windows, Linux, ChromeOS
Enables showing password suggestions without requiring the user to click on the already focused field if the field was autofocused on the page load. – Mac, Windows, Linux, ChromeOS, Android
If this client is a Google-internal dogfood client, overrides enterprise policy to enable model quality logs. Googlers: See go/chrome-mqls-debug-logging for details. – Mac, Windows, Linux, ChromeOS, Android
Enable the WebAuthn Conditional Create feature and let websites automatically create passkeys in GPM if there is a matching password credential for the same user. – Mac, Windows, Linux, ChromeOS
When enabled, line breaking doesn't happen inside <ruby>s with shorter contents even if `text-wrap: nowrap` is not specified. – Mac, Windows, Linux, ChromeOS, Android
Enables the exploratory Prompt API, allowing you to send natural language instructions to a built-in large language model (Gemini Nano in Chrome). Exploratory APIs are designed for local prototyping to help discover potential use cases, and may never launch. These explorations will inform the built-in AI roadmap [1]. This API is primarily intended for natural language processing tasks such as summarizing, classifying, or rephrasing text. It is NOT suitable for use cases that require factual accuracy (e.g. answering knowledge questions). You must comply with our Prohibited Use Policy [2] which provides additional details about appropriate use of Generative AI. – Mac, Windows, Linux, ChromeOS, Android
Extends the exploratory Prompt API with image and audio input types. Allows you to supplement natural language instructions for a built-in large language model (Gemini Nano in Chrome) with image and audio inputs. Exploratory APIs are designed for local prototyping to help discover potential use cases, and may never launch. These explorations will inform the built-in AI roadmap [1]. This API enhancement is primarily intended for natural language processing tasks associated with visual and auditory data, such as generating rough descriptions of pictures and sounds. It is NOT suitable for use cases that require factual accuracy (e.g. answering knowledge questions). You must comply with our Prohibited Use Policy [2] which provides additional details about appropriate use of Generative AI. – Mac, Windows, Linux, ChromeOS, Android
Enables the Summarization API, allowing you to summarize a piece of text with a built-in large language model (Gemini Nano in Chrome).The API may be subject to changes including the supported options.Please refer to the built-in AI article [1] for details. This API It is NOT suitable for use cases that require factual accuracy (e.g. answering knowledge questions). You must comply with our Prohibited Use Policy [2] which provides additional details about appropriate use of Generative AI. – Mac, Windows, Linux, ChromeOS, Android
Enables the Writer API, allowing you to write a piece of text with a built-in large language model (Gemini Nano in Chrome).The API may be subject to changes including the supported options.Please refer to the built-in AI article [1] for details. You must comply with our Prohibited Use Policy [2] which provides additional details about appropriate use of Generative AI. – Mac, Windows, Linux, ChromeOS, Android