Coding agentGoogleConfirmed
Story 12 of 17 in the Wednesday 4 November editionGoogle makes the Gemini API Computer Use tool generally available for agents
Supported on Gemini 4 and Gemini 3.x models with zero breaking changes from preview, the tool drives browser, mobile and desktop interfaces with safety overrides.
Google made the Computer Use tool generally available in the Gemini API on 4 November 2026 with no breaking changes from preview, enabling Gemini 4 and Gemini 3.x models to inspect screenshots and emit UI actions with per-step intent reasoning, configurable safety policy overrides and opt-in screenshot prompt-injection scanning across browser, mobile and desktop client environments.
Sources
- PrimaryGemini API Computer Use documentationaistudio.google.com
- On XGoogle AI Studio general availability post on Xx.com
The rest of the day
Read the whole day01CreativeOpenAI
OpenAI rolls out ChatGPT Images 2.6 with animated GIFs and two new API image models
Images 2.6 generates visuals 50% faster across ChatGPT and Codex while adding GPT-Image-2.6 Flare and Sunburst to the API with SVG export and markup-guided edits.
02ModelTencent
Tencent launches multimodal Hy4 model with native computer use and 3D engine training
Hy4 adds visual reasoning alongside CLI and GUI control, trained directly inside Blender, CAD, Unreal Engine, Unity and Godot environments.
03Open sourceMoonshot AI
Moonshot AI releases open-weight Kimi K3.1 Pro with 2.8T parameters and 1M context
Activating 104B parameters per token with native MXFP4 weights, the multimodal MoE model leads Opus 5.5 and GPT-6 Astra on SWE Marathon v1.1.
04ResearchOpenAI
OpenAI’s autonomous cyber pipeline uncovers and patches 948 Linux kernel root flaws
Powered by an upcoming cyber model, a five-stage VM validation and exploit pipeline generated working privilege-escalation exploits at $1,279 per distinct vulnerability.
Spotted an error? Email aiforsuccess.in+compass@gmail.com or tag @ai_for_success on X







