
Alexis Moussine-Pouchkine
@alexismp
Followers
5K
Following
14K
Media
913
Statuses
16K
Google Cloud Developer Relations EMEA. Java/Sun veteran. Tennis connoisseur.
Paris. Usually.
Joined June 2007
I've been using the agent mode of Code Assist for a couple of weeks now and find myself also using Gemini CLI on the side (or in a VS Code terminal), sometimes even in parallel. #righttoolforthejob.
No longer exclusively in the "Insiders" build, Gemini Code Assist now offers agent mode to *everyone*. It's powered by the Gemini CLI, so get all the MCP extensibility and multi-step smarts built in. Docs:
0
0
3
RT @GoogleDeepMind: Our new AI model AlphaEarth Foundations is mapping the planet in astonishing detail. 🌏🔍. Scientists will now be able to….
0
665
0
RT @danicat83: Do you want to learn more about how to build an MCP server in #golang? Your problems are solved!!!😁Check my latest article:….
danicat.dev
A step-by-step guide on how I built GoDoctor, an AI-powered Go development assistant, using the Model Context Protocol (MCP) and the Gemini CLI.
0
3
0
RT @NotebookLM: Seeing all the articles and blog posts about the new video overviews launch but don’t have the time to read them all?. We g….
0
184
0
RT @ryanjsalva: A PSA for all our CLI weekend warriors and Sunday fun-day vibe coders. Gemini CLI is a powerful tool. Use the safeguards:….
0
6
0
RT @ivnardini: 🚀 ADK v1.8.0 just dropped!. This release is packed with new tools for enhanced agent development and deployment. Feature hi….
0
8
0
hey @geminicli, look at all the pictures with a name starting with DSC and for each one rename it to what's in the photo and add a suffix if the image is blurry.
1
0
0
LLM Evals are hard, this is a welcome announcement.
🚀 Kaggle Benchmarks is here! Get competition-grade rigor for AI model evaluation. Let Kaggle handle infrastructure while you focus on AI breakthroughs. View model performance on 70+ leaderboards, including @AIatMeta's MultiLoKo. Dive in:
0
0
3
Yep, 10¢/1M input and 40¢/1M output tokens. and amazingly low latency.
Gemini 2.5 Flash-Lite is now stable and GA!🚀. It is our most cost-efficient, fastest, and cheapest 2.5 model, priced at $0.10/1M input and $0.40/1M output tokens. It has lower latency than 2.0 Flash and shows great performance on a wide range of tasks!.
1
1
3
RT @patloeber: Gemini 2.5 Flash-Lite is now stable and GA!🚀. It is our most cost-efficient, fastest, and cheapest 2.5 model, priced at $0.1….
developers.googleblog.com
0
9
0
RT @ntaylormullen: Gemini CLI key highlights for week of 7/14/2025. - 🎉 Gemini CLI v1 Roadmap: - Show modified con….
0
45
0