The LGTM (Page 89)

The LGTM

Sign in Subscribe

GitHub’s ‘Fix with Copilot’ Button Is a CI Shortcut With a Governance Problem Attached

GitHub’s ‘Fix with Copilot’ Button Is a CI Shortcut With a Governance Problem Attached

GitHub’s new Fix with Copilot button looks like the smallest possible product feature: a failed GitHub Actions run gets a button, Copilot cloud agent investigates, pushes a fix to the branch, and tags the developer for review. Cute. Also: this is exactly where coding agents stop being autocomplete and

xAI's Tax-Return Training Gambit Is a Data Governance Story Wearing a $420 Joke

xAI's Tax-Return Training Gambit Is a Data Governance Story Wearing a $420 Joke

xAI’s latest training-data story looks like a workplace punchline until you read it as infrastructure. Bloomberg reports that managers asked employees to hand over completed tax returns and supporting documents so Grok could get better at tax-preparation tasks, with a promised $420 payment per submission and early access to

Dell Gives Codex the Enterprise Shortcut: Put the Agent Where the Data Already Lives

OpenAI’s Dell partnership is not a flashy model launch. Good. The next bottleneck for coding agents is not whether they can write another React component from a clean prompt. It is whether they can operate near the messy, governed, high-value context enterprises actually use without turning every security review

Anthropic Buying Stainless Is a Bet That Agent UX Starts at the API Boundary

Anthropic Buying Stainless Is a Bet That Agent UX Starts at the API Boundary

Anthropic did not buy Stainless because SDK generation is a nice developer-experience accessory. It bought the compiler layer between APIs and agents. That distinction matters. The company’s announcement is short, almost aggressively calm: Stainless has generated every official Anthropic SDK since the early Claude API days; it turns API

InsForge Is the Backend Branching Layer Claude Code Keeps Needing After the Demo

InsForge Is the Backend Branching Layer Claude Code Keeps Needing After the Demo

Claude Code is good at editing files. The industry’s next problem is that useful software is no longer only files. Modern apps come attached to Postgres schemas, auth providers, storage buckets, edge functions, cron jobs, realtime channels, deployment targets, secrets, logs, and increasingly a model gateway. That is the

Discord Needs the Same Ingress Isolation Telegram Just Got

Discord Needs the Same Ingress Isolation Telegram Just Got

A chat bot that takes four seconds to notice a message does not feel “under load.” It feels absent. That is the product problem behind OpenClaw issue #83591, which argues that Discord needs the same ingress isolation Telegram recently received. The technical complaint is about event loops, worker threads, WebSockets,

OpenClaw Is Finally Treating models.json Like Prompt-Visible Attack Surface

OpenClaw Is Finally Treating models.json Like Prompt-Visible Attack Surface

There are security bugs that announce themselves with a CVE and a diagram. Then there are the quieter ones: a config file becomes prompt-visible, a generated catalog preserves a plaintext API key, and suddenly the language model is sitting inside your credential boundary because everyone agreed to call it “metadata.

Codex-in-Docker Still Trips Over bwrap Because Sandbox Layers Need a Contract

Codex-in-Docker Still Trips Over bwrap Because Sandbox Layers Need a Contract

Codex versus Claude is usually framed as a model-quality argument: who writes better code, who follows instructions better, who burns fewer tokens getting there. That framing is too narrow. The more operational question is whether the agent can reliably reach a shell, run the command it planned, and report the

GitHub Copilot’s New Default Model Is Really an Enterprise Change-Control Story

GitHub Copilot’s New Default Model Is Really an Enterprise Change-Control Story

GitHub’s latest Copilot change looks like the usual model shuffle: GPT-5.3-Codex is now the base model for Copilot Business and Copilot Enterprise, replacing GPT-4.1 for organizations without approved alternatives. The more important story is less glamorous and more useful: GitHub is quietly turning model selection into enterprise