Computer use in Gemini 3.5 Flash

	Computer use in Gemini 3.5 Flash(blog.google)
	231 points by swolpers 20 hours ago \| 148 comments
	tl;dr: Google has integrated computer use as a built-in tool in Gemini 3.5 Flash, allowing developers to build agents that interact with browsers, mobile, and desktop environments without relying on the previous standalone Gemini 2.5 computer use model. To address prompt injection risks, Google added adversarial training plus optional enterprise safeguards like requiring user confirmation for sensitive actions and auto-stopping tasks on detected injections. It's available now via the Gemini API and Enterprise Agent Platform.
	HN Discussion: ↓Gemini models are unreliable and prone to hallucination or giving up on tasks ↓Computer use approaches are fundamentally flawed - slow, insecure, and inferior to API/accessibility tree methods ↓Google lacks a competitive Codex/Claude Code equivalent and proper MCP support ↓Gemini's guardrails are overtuned, refusing benign requests ↓Google's own benchmarks show Gemini 3.5 Flash losing to competitors despite framing