The LGTM (Page 79)

The LGTM

Home
Agentic Coding
Claude Code
Codex

Sign in Subscribe

Prompt Flow's Retirement Notice Is a 12-Month Migration Warning, and the Real Work Starts Now, Not in April 2027

Prompt Flow's Retirement Notice Is a 12-Month Migration Warning, and the Real Work Starts Now, Not in April 2027

On April 30, Microsoft formally told the world that Prompt Flow is going away. The retirement announcement gave teams twelve months — until April 20, 2027 — before Prompt Flow enters read-only mode and existing flows keep running but nothing new gets built. Feature development stopped April 20, 2026. Only security patches

02 May 2026 3 min read

DeepSeek V4 Lands in Microsoft Foundry, and the Real Story Is Microsoft's Model-Arbitrage Infrastructure Play

There is a version of this story that writes itself: Microsoft added DeepSeek V4 to Azure Foundry, here is the price, here is the context window, go forth and integrate. That version would take about four paragraphs, link to the Microsoft post, and call it done. It would also miss

02 May 2026 4 min read

The Four Layers of AI Agent Development That Actually Work

Most developers who picked up AI coding tools in the past eighteen months have had the same experience. It works beautifully — until it doesn't. You start a project, you prompt, you iterate, you ship. Then the codebase grows. More services, more state, more API surface. The agent starts

02 May 2026 6 min read

Gemini CLI's Offline Ripgrep Push Is Google Finally Taking Local-First Coding Agents Seriously

Gemini CLI's Offline Ripgrep Push Is Google Finally Taking Local-First Coding Agents Seriously

Gemini CLI's Offline Ripgrep Push Is Google Finally Taking Local-First Coding Agents Seriously There is a version of the Gemini CLI story that reads as a routine patch release with some nightly-build noise attached. That is the version that surfaces in your feed, gets a two-paragraph summary, and

02 May 2026 6 min read

The Model That Won the Volume War (And the One That Bought It)

The Model That Won the Volume War (And the One That Bought It)

May 2, 2026 If you've been watching the LLM leaderboards lately and wondering why the model that tops the benchmark wars keeps losing marketshare to cheaper alternatives — today's data snapshot is for you. The Arena Text leaderboard for May 1, 2026 reads like a coronation ceremony

02 May 2026 5 min read

The Goblin Ban in OpenAI's Codex Is a Window Into How Production AI Coding Agents Actually Work

OpenAI published an unusually candid explainer on Thursday titled "Where the Goblins Came From" — a post that started as a joke on social media and turned into the most concrete public accounting the company has ever given of how reward signals in reinforcement learning can produce behavior that

02 May 2026 4 min read

OpenClaw's New Runtime-Context Leak Is a Good Reminder That Hidden Metadata Is Only Hidden Until the Model Says It Out Loud

OpenClaw's New Runtime-Context Leak Is a Good Reminder That Hidden Metadata Is Only Hidden Until the Model Says It Out Loud

There is a specific kind of bug that only shows up under pressure. Not a crash that leaves a stack trace. A regression that feels like a weird user experience problem until you trace it back and realize the runtime itself is saying something it should not be saying. That

01 May 2026 4 min read

NVIDIA's Kernel Translation Skill Is the Most Honest Thing the Company Has Published About AI Coding Agents

The first time an AI model silently breaks a GPU kernel, it will not crash. It will not error. It will produce wrong answers and look correct doing it. That is the core tension in NVIDIA's latest TileGym post on automated kernel translation — and the reason the post

01 May 2026 4 min read

Microsoft Agent Framework 1.2.2 Is the Patch That Makes the Enterprise Agent Story Actually Hang Together

Microsoft Agent Framework 1.2.2 Is the Patch That Makes the Enterprise Agent Story Actually Hang Together

Microsoft shipped agent-framework Python 1.2.2 on April 29, and if you are still evaluating this framework based on whether it has good agent abstractions, you are asking the wrong question. The more important thing to understand about this release is what the additions say about Microsoft's

01 May 2026 5 min read

Claude Opus 4.7 Is Now GA on GitHub Copilot — and the Promotional Pricing Window Just Closed

Claude Opus 4.7 Is Now GA on GitHub Copilot — and the Promotional Pricing Window Just Closed

GitHub confirmed this week that Claude Opus 4.7 is now generally available across every Copilot surface — VS Code, Visual Studio, Copilot CLI, JetBrains, Xcode, Eclipse, GitHub.com, GitHub Mobile, and the cloud agent. The announcement came with an editor's note that is worth reading twice: the promotional

01 May 2026 5 min read

GitHub Copilot's Surprise Announcement: Sign-Ups Paused, Opus Evicted From Pro, Rate Limits Now Visible

GitHub Copilot's Surprise Announcement: Sign-Ups Paused, Opus Evicted From Pro, Rate Limits Now Visible

GitHub's April 30 announcement reads like a product retraction dressed as a billing update. New sign-ups for Copilot Pro, Pro+, and Student are paused indefinitely. Opus-family models are gone from Copilot Pro entirely. Rate limits are now visible in VS Code and the CLI instead of hiding behind

01 May 2026 4 min read

Microsoft Just Named the AI Coding Security Gap That's Been Hiding in Plain Sight

Microsoft Just Named the AI Coding Security Gap That's Been Hiding in Plain Sight

Microsoft published a policy essay on May 1 that should be required reading for anyone deploying AI coding tools in a production environment. The post — on the company's On the Issues blog, written from the security and policy organization rather than a product team — makes a specific argument

01 May 2026 4 min read

← Newer Posts Page 79 of 114 Older Posts →

The LGTM © 2026

Sign up

Powered by Ghost