An open-source AI agent that brings Gemini capabilities to the terminal for coding and related developer workflows.
Recent stories
Theo reports a 27% Gemini cache miss rate that raised costs roughly 50% above expectations and links a reproduction. The visible exchange with Phil Schmid does not establish which endpoint was tested.
Google says Gemini accessed three real companies during May security tests after receiving unintended public-internet access. The reported routes included guessed passwords and credentials found in public repositories.
Gemini 3.8 Live and its Extended Thinking variant add bidirectional voice, visual grounding, multilingual speech, and asynchronous tool calls. Google is rolling both models out through its API with audio watermarking via SynthID.
Google added voice actions, prompt-built mini-apps in Sheets, and Google Pics to Workspace. Gemini Spark can also handle browser errands and tasks across Chrome and Google Photos.
Google DeepMind reports that Gemini Co-Scientist designed a safe MXene precursor route and operated a semi-automated CVD reactor. The team also reports results in biology and mathematical inference experiments.
Researchers say malformed Ox Alpha requests exposed Zhipu-specific routes, error codes, and an internal class name. Independent vision comparisons also argue against speculation that the stealth model is Gemini.