The  LGTM
  • Home
  • Agentic Coding
  • Claude Code
  • Codex
Sign in Subscribe
AI Coding-Agent Security Is a Runtime Problem Wearing a Model-Safety Costume
codex

AI Coding-Agent Security Is a Runtime Problem Wearing a Model-Safety Costume

The most useful security line written about AI coding agents this week did not come from a model card. It came from VentureBeat quoting Enkrypt AI CSO Merritt Baer: “The runtime is the blast radius.” That is the sentence the industry needs to sit with for a while, because it
21 Apr 2026 5 min read
Azure Developer CLI’s New Copilot Integration Is Microsoft’s Best Current Case for AI That Fixes Plumbing Instead of Writing Poetry
azure-ai

Azure Developer CLI’s New Copilot Integration Is Microsoft’s Best Current Case for AI That Fixes Plumbing Instead of Writing Poetry

Microsoft keeps trying to convince developers that Copilot belongs everywhere. Most of those pitches have felt like product management mistaking proximity for usefulness. Put AI in the sidebar, put AI in the editor, put AI in the document toolbar, and maybe one of those surfaces will stick. The new GitHub
21 Apr 2026 5 min read
azure-ai

Microsoft Foundry’s Private Networking Story Gets Real Once You Stop Confusing Private Endpoints with Actual Runtime Isolation

Microsoft’s latest Azure AI lesson is not about model quality, prompt engineering, or the next catalog addition. It is about a much older enterprise problem: people keep confusing a network diagram with an actual runtime boundary. That distinction sounds boring right up until an AI agent that looked safely
21 Apr 2026 4 min read
Security Copilot’s New Email Summary Feature Shows Where Microsoft Thinks SOC Automation Can Safely Start
azure-ai

Security Copilot’s New Email Summary Feature Shows Where Microsoft Thinks SOC Automation Can Safely Start

Security teams do not need AI to write poetry about phishing. They need it to make the first five minutes of investigation less miserable. That is why Microsoft’s new Email Summary capability inside Defender is worth paying attention to. It is not flashy, and that is the point. Microsoft
21 Apr 2026 4 min read
Copilot in Word Is Finally Moving From ‘Generate Some Text’ to ‘Help Me Survive Document Review’
azure-ai

Copilot in Word Is Finally Moving From ‘Generate Some Text’ to ‘Help Me Survive Document Review’

Microsoft has spent the better part of the Copilot era teaching the world to ask office software for first drafts. The problem is that first drafts were never the expensive part of knowledge work. The expensive part is review: reconciling tracked edits, chasing comment threads, spotting ambiguity before legal does,
21 Apr 2026 4 min read
Microsoft’s Agent Governance Push Is Really an Azure App Hosting Story in Disguise
azure-ai

Microsoft’s Agent Governance Push Is Really an Azure App Hosting Story in Disguise

Microsoft’s latest agent governance push is notable for what it is not. It is not another benchmark post about reasoning, not another framework launch, and not another reminder that everyone suddenly has an agent strategy. It is a much more practical statement: if enterprises are going to let AI
21 Apr 2026 4 min read
xAI's Docs Refresh Says the Company Is Finally Thinking Like a Cloud Vendor
xai

xAI's Docs Refresh Says the Company Is Finally Thinking Like a Cloud Vendor

For most AI companies, the fun part of the story is the model. For anyone responsible for a budget, the real story starts when the pricing page gets complicated. That is why the most revealing part of xAI’s docs refresh is not another Grok model row. It is that
21 Apr 2026 5 min read
xAI Quietly Turned Grok Into a Real Speech Stack
xai

xAI Quietly Turned Grok Into a Real Speech Stack

xAI has spent the last year being covered like a consumer AI company with a spicy chatbot attached to a billionaire soap opera. The more interesting story, at least for people who actually ship software, is that its docs now describe something much more consequential: a reasonably complete speech stack.
21 Apr 2026 5 min read
The Vercel Breach Is a Warning About the Trust Boundaries AI Coding Tools Inherit for Free
agentic-coding

The Vercel Breach Is a Warning About the Trust Boundaries AI Coding Tools Inherit for Free

The Vercel breach is not an “AI incident” in the narrow marketing sense, and that is exactly why people building with coding agents should pay attention. It is a plain old identity and supply-chain mess, the kind the software industry keeps producing because convenience gets approved faster than boundaries. The
21 Apr 2026 5 min read
GitHub Just Admitted Agentic Coding Broke the Old Copilot Pricing Model
agentic-coding

GitHub Just Admitted Agentic Coding Broke the Old Copilot Pricing Model

GitHub’s latest Copilot change looks like pricing churn on the surface, but the more interesting story is that one of the biggest developer platforms on earth just said the quiet part out loud: agentic coding is expensive enough to break the old subscription math. That matters because the first
21 Apr 2026 5 min read
Lovable’s Leak Mess Shows Vibe Coding Still Has a Basic Security Discipline Problem
agentic-coding

Lovable’s Leak Mess Shows Vibe Coding Still Has a Basic Security Discipline Problem

Lovable’s security mess is useful precisely because it is not subtle. The company spent the first part of the incident doing what too many fast-growing AI products still do when confronted with a bug that looks bad in screenshots: argue about semantics before fixing the trust problem people can
21 Apr 2026 4 min read
Google’s Pomelli Expansion Shows the Real Small-Business AI Fight Is Moving From Chatbots to Creative Ops
google-ai

Google’s Pomelli Expansion Shows the Real Small-Business AI Fight Is Moving From Chatbots to Creative Ops

Google’s Pomelli expansion is easy to dismiss if you only read the press-release nouns. Another AI marketing tool. Another Labs experiment. Another attempt to help small businesses generate content faster. Fine. But that reading undersells what is actually happening. Pomelli is a much clearer signal than most consumer-facing AI
21 Apr 2026 5 min read
← Newer Posts Page 103 of 119 Older Posts →
The LGTM © 2026
  • Sign up
Powered by Ghost