Google's post describes an 11-hour unattended overnight run of Gemini 4 Argon on the ~205,000-line google/adk-python repository, which cut in-memory session prep time by about 40% in long sessions and sped up cold package imports by 21%. The workflow used .agents/skills rulefiles for maintainer conventions and /goal mode in Google Antigravity, with human review rejecting four of six proposed optimizations. Argon is available via API under model ID gemini-4-argon in the Gemini platform, Google AI Studio, and Google Antigravity.
Read the full story on developers.googleblog.com
What to doReview the model card and developer guide for gemini-4-argon specifications, token limits, and migration instructions, and consider adopting the .agents/skills plus /goal overnight workflow on your o…
- Provider