Anatoliy Kolodkin - The LGTM (Page 46)

The LGTM

Sign in Subscribe

Anatoliy Kolodkin

Microsoft Is No Longer Content Renting the Frontier — MAI Is Its Bid for AI Self-Sufficiency Inside Azure

Microsoft Is No Longer Content Renting the Frontier — MAI Is Its Bid for AI Self-Sufficiency Inside Azure

Microsoft’s relationship with OpenAI is no longer the whole Azure AI story. That does not mean Microsoft is breaking up with the lab it helped bankroll with more than $13 billion. It means the company has decided that renting the frontier is not enough when the frontier is now

OpenAI’s Codex Credits Page Is the Budget Policy Engineering Teams Actually Need

OpenAI’s Codex Credits Page Is the Budget Policy Engineering Teams Actually Need

The most important Codex feature this week is not a new editor trick, a bigger context window, or another agent surface. It is a billing control. That sounds like accountant bait until you remember what coding agents have become: long-running, tool-using, sometimes-parallel workers that can burn real money while producing

Copilot’s GPT-5.2 Cutover Is a Model-Routing Drill, Not Just a Dropdown Cleanup

Copilot’s GPT-5.2 Cutover Is a Model-Routing Drill, Not Just a Dropdown Cleanup

Model deprecations used to be a mild annoyance: a dropdown changed, autocomplete felt different for a week, and everyone moved on. In 2026, that is not how coding agents work. When GitHub removes GPT-5.2 and GPT-5.2-Codex from most Copilot surfaces, it is not cleaning up a menu. It

Claude Agent SDK Parity Releases Make Headless Agents Inherit the Same Runtime Rules as Claude Code

Claude Agent SDK Parity Releases Make Headless Agents Inherit the Same Runtime Rules as Claude Code

The Claude Agent SDK parity releases look like changelog dust until you remember where SDKs run. Claude Code is the visible tool: a terminal, prompts, permissions, MCP wiring, background sessions, and a human close enough to notice when something gets weird. The Agent SDK is the embedding surface. It is

Anthropic’s SDKs Just Moved Managed Agents From Preview Docs Toward Real Client Surface Area

Anthropic’s SDKs Just Moved Managed Agents From Preview Docs Toward Real Client Surface Area

Anthropic’s latest SDK releases are not trying to win the launch thread. That is probably the point. TypeScript v0.102.0 and Python v0.107.0, both published on June 6, move Managed Agents a little further out of “interesting beta documentation” and into the place production teams actually

xAI’s Colossus Buildout Is Starting to Look Like a Neocloud With a Chatbot Attached

xAI’s Colossus Buildout Is Starting to Look Like a Neocloud With a Chatbot Attached

Colossus was supposed to be the engine behind Grok. The more interesting version of the story, at least this week, is that it may be becoming something less glamorous and more valuable: scarce AI infrastructure rented by the month to the companies Grok is trying to beat. TechCrunch reports that

Mastra 1.41 Turns Sandboxes Into a Multi-Tenant Runtime Decision

Mastra 1.41 Turns Sandboxes Into a Multi-Tenant Runtime Decision

Mastra 1.41 is the kind of release that looks boring until you have actually tried to ship an agent product with more than one customer. Then it looks less like plumbing and more like the boundary between a demo and an incident report. The headline change in @mastra/core

Fix with Copilot Turns Failed GitHub Actions Into Agent Work. Useful, If You Keep the Blast Radius Small.

Fix with Copilot Turns Failed GitHub Actions Into Agent Work. Useful, If You Keep the Blast Radius Small.

“Fix with Copilot” for failing GitHub Actions is a genuinely good agent use case, which is precisely why it deserves more scrutiny than the average AI button. CI failures are narrow, evidence-rich, and measurable. They are also where teams often confuse “green” with “correct.” GitHub has put an agent directly