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]
Free Gemini CLI gets a deadline as terminal agents move to Antigravity

Free Gemini CLI gets a deadline as terminal agents move to Antigravity

Google is moving the personal and free Gemini CLI path to Antigravity CLI. The June 18 cutoff marks a shift in the operating layer for coding agents.

Claude Platform on AWS is a native path outside Bedrock

Claude Platform on AWS is a native path outside Bedrock

Claude Platform on AWS brings Anthropic native features into AWS procurement and IAM, but its data boundary is not the same as Bedrock.

The switch to review before August 17, Atlassian AI data contribution

The switch to review before August 17, Atlassian AI data contribution

Atlassian data contribution settings show how Jira, Confluence, Rovo, and Teamwork Graph data defaults now shape AI improvement loops.

Codex Goals and the New Completion Contract for Coding Agents

Codex Goals and the New Completion Contract for Coding Agents

OpenAI Codex Goals turns long-running coding work into an evidence-based loop with objectives, verification surfaces, constraints, and budgets.

KPMG puts Claude inside the tax and legal workbench

KPMG puts Claude inside the tax and legal workbench

Anthropic and KPMG are turning Claude into an agent layer for Digital Gateway, private equity modernization, and Big Four delivery.

11 Seconds of Audio in Under 8 Seconds, Without a GPU

11 Seconds of Audio in Under 8 Seconds, Without a GPU

Google and Arm show how on-device generative AI is moving from model releases into CPU runtimes, quantization, memory limits, and silicon features.

Composer 2.5 shows Cursor training for reward hacking

Composer 2.5 shows Cursor training for reward hacking

Cursor Composer 2.5 shows the coding-agent race shifting from benchmark scores toward long-task failure points, targeted feedback, and reward-hacking detection.

Google AI Overviews exposes the gap behind citation cards

Google AI Overviews exposes the gap behind citation cards

A May 13 arXiv study measured 55K Google searches and 98K AI Overview claims, showing where citations, ranking, and publisher economics diverge.

ECHO makes stderr part of the coding agent world model

ECHO makes stderr part of the coding agent world model

Microsoft Research ECHO turns terminal output into a direct learning signal so coding agents can learn from failed logs, not only final rewards.

Copilot remote control turns coding agents into an operations layer

Copilot remote control turns coding agents into an operations layer

GitHub’s May 18 Copilot updates link remote control, low-cost models, CI repair, and audit APIs into a control plane for coding agents.

Genkit Middleware Moves Agent Control Outside the Prompt

Genkit Middleware Moves Agent Control Outside the Prompt

Google Genkit Middleware shows how retries, fallback, tool approval, and filesystem boundaries are moving into the runtime layer of agent apps.

arXiv one-year bans show the trust cost of AI citations

arXiv one-year bans show the trust cost of AI citations

arXiv scrutiny of AI-generated manuscripts is not a blanket LLM ban. It is a warning about hallucinated citations entering research infrastructure.