Tech Tips
Google ADK Live Evaluation: Test Voice Agents Before Shipping
Google ADK now lets teams regression-test live voice agents with synthetic audio, tool assertions, and multi-turn rubrics.
Topic · 13 stories#google
Reporting, analysis and practical guides connected to google.
Latest in #google
Newest first
Reviews
Google Antigravity: Is the Agent-First IDE Worth It in 2026?
Google Antigravity is a VS Code fork built around autonomous agents, with a Manager View that dispatches up to five parallel agents and a built-in Chrome browser for front-end verification. Gemini is the default model, with Claude and GPT supported. Strengths are parallel-agent workflow and browser verification; weaknesses are shifting credit-based pricing, a five-agent cap, and a closed-source core. The verdict: a strong secondary tool, especially for front-end and Gemini-centric workflows.
AI News
Gemini 3.5 Flash: The Flash Model That Beats Google's Own Pro Tier
Google released Gemini 3.5 Flash on May 19, 2026, at Google I/O. The Flash-tier model beats Gemini 3.1 Pro on coding and agentic benchmarks (76.2% Terminal-Bench 2.1, 83.6% MCP Atlas, 1656 GDPval-AA Elo) while running 4x faster and costing $1.50/$9 per 1M tokens, 40% below 3.1 Pro. It trails Pro on academic reasoning (Humanity's Last Exam, ARC-AGI-2) and dense long-context recall. It powers Gemini Spark, Antigravity 2.0, and is now the default model for the Gemini app and AI Mode in Search.
Reviews
Google Antigravity 2.0: From Cursor Clone to AI Agent Platform
A hands-on review of Google Antigravity 2.0: its multi-agent orchestration, pricing, and trade-offs.
AI News
Apple Siri: Why Apple Is Paying Google $1B for Gemini
At WWDC 2026, Apple unveiled a rebuilt Siri powered by a custom, Apple-tuned Google Gemini model—reportedly a 1.2-trillion-parameter mixture-of-experts system costing roughly $1 billion a year. On-device Apple Silicon models handle quick private tasks, while complex reasoning routes to the Gemini model inside Apple's Private Cloud Compute, with a contract barring Google from training on Apple user data.
AI News
Gemma 4 12B: Google's Encoder-Free Multimodal Laptop Model
Google released Gemma 4 12B on June 3, 2026, a multimodal open model with an encoder-free architecture that feeds vision and audio directly into the LLM backbone. It runs locally on 16GB of memory, approaches the 26B MoE on benchmarks, uses Multi-Token Prediction drafters for low latency, and ships under Apache 2.0 with broad tooling support.
AI News
Gemini 3.5 Flash: Google's Flash Tier Eats Pro on Agent Benchmarks
Gemini 3.5 Flash outperforms the Pro tier on agent benchmarks with superior speed and efficiency.
Deep Dives
WebMCP: Inside Chrome 149's Plan to Kill DOM-Scraping Agents
WebMCP in Chrome 149 aims to replace DOM-scraping agents with structured tools and policies.
AI News
Gemini Spark: Google's 24/7 Agent Runs Even When You Close Your Laptop
Gemini Spark is Google's 24/7 agent that continues working even when your laptop is closed.
Deep Dives
TurboQuant: Google's 6x KV Cache Compression Hits 3-Bit With Zero Loss
Google's TurboQuant compresses KV cache 6x at 3 bits with zero loss, speeding up attention.
Tech Tips
Gemini API Webhooks: Kill the Polling Loop on Long-Running Jobs
Google's Gemini API Webhooks eliminate polling loops for long-running jobs, simplifying integration.
AI News
Vision Banana: DeepMind Beats SAM 3 and Depth Anything V3
DeepMind's Vision Banana outperforms leading models, suggesting generation is key for vision pretraining.
Open Source
Gemini CLI: Google's Open-Source Terminal Agent Hits 101K GitHub Stars
Google's Gemini CLI, an open-source terminal AI agent, hits 101K GitHub stars with new features.
