Devlery
BlogSkillsTags

Blog

Notes and analysis on AI development.

All [496]AI [495]AI Agent [443]AI Infrastructure [311]Developer Tools [305]AI Coding [188]LLM [135]Security [109]AI News [52]MCP [33]Open Source [29]AI Safety [23]Productivity [10]Enterprise [7]Gemini [6]Microsoft [6]Anthropic [4]DevOps [4]AI Search [3]Claude Code [3]GitHub [3]OpenAI [3]ChatGPT [2]Data [2]AI Ethics [1]AI Governance [1]Android [1]AWS [1]Education [1]Fintech [1]Google [1]Meta [1]Policy [1]Robotics [1]Vercel [1]Workflow [1]
LiteRT-LM WebGPU brings local agents into the browser

LiteRT-LM WebGPU brings local agents into the browser

Google LiteRT-LM expands Gemma 4 local inference across Android, iOS, WebGPU, and CLI, changing where AI apps can run.

Gemini Omni Flash Turns Video Editing Into a Conversation

Gemini Omni Flash Turns Video Editing Into a Conversation

Gemini Omni Flash reframes AI video generation as an interactive editing loop connected to Google Flow and YouTube Shorts.

Android Inside AI Studio, and the App Bottleneck Moves to the Browser

Android Inside AI Studio, and the App Bottleneck Moves to the Browser

Google AI Studio now reaches Android app generation and Play testing paths, moving the AI app bottleneck from prompting to verification.

Vera CPU ships first, and the agent bottleneck moves beyond GPUs

Vera CPU ships first, and the agent bottleneck moves beyond GPUs

NVIDIA Vera CPU systems have reached OpenAI, Anthropic, SpaceXAI, and OCI. Agent infrastructure is becoming a CPU runtime problem, not just a GPU race.

WebMCP Origin Trial turns browser agents from click guessers into tool users

WebMCP Origin Trial turns browser agents from click guessers into tool users

Chrome WebMCP is an Origin Trial for exposing structured tools and permission boundaries from web apps to browser agents.

AlphaEvolve cuts errors 30% and turns coding agents into scientific infrastructure

AlphaEvolve cuts errors 30% and turns coding agents into scientific infrastructure

AlphaEvolve extends Gemini-based coding agents into evaluated loops for genomics, quantum simulation, infrastructure scheduling, and algorithm discovery.

DevTools 1.0 sets a browser QA baseline for coding agents

DevTools 1.0 sets a browser QA baseline for coding agents

Chrome DevTools for agents 1.0 pulls coding agents into real browser QA and debugging loops.

Four-Nines Agents on Kafka, Confluent Bets on Real-Time AI

Four-Nines Agents on Kafka, Confluent Bets on Real-Time AI

Confluent Intelligence Q2 turns Kafka and Flink streams into real-time context, control, and security infrastructure for AI agents.

When Flash Beats Pro, Agent Economics Take Over

When Flash Beats Pro, Agent Economics Take Over

Gemini 3.5 Flash is not just another fast model release. It points to the cost, latency, and routing fight behind coding agents and AI search.

When the search box becomes a 24-hour agent, Google tests mini apps

When the search box becomes a 24-hour agent, Google tests mini apps

Google Search agents extend search from answers into persistent monitoring, task state, alerts, and generative UI mini apps.

Dell puts agents beside the desk, and token location becomes infrastructure

Dell puts agents beside the desk, and token location becomes infrastructure

Dell Deskside Agentic AI reframes agent deployment around local workstations, data proximity, sandboxed runtimes, and the economics of repeated inference.

Gemini API Managed Agents turn model calls into sandboxed workers

Gemini API Managed Agents turn model calls into sandboxed workers

Google Gemini API Managed Agents move model calls into isolated Linux sandboxes with stateful agent execution.