The LGTM (Page 87)

The LGTM

Home
Agentic Coding
Claude Code
Codex

Sign in Subscribe

GitHub's Honest Accounting of How Agentic Coding Broke Its Architecture

GitHub's Honest Accounting of How Agentic Coding Broke Its Architecture

GitHub published something unusual this morning: an honest postmortem. Not the careful, vaguely apologetic kind that blames vendors or mysterious "upstream providers." A real one. The short version: the platform that hosts over 100 million developers woke up to the fact that its architecture was designed for humans

28 Apr 2026 4 min read

The Real LLM Rankings Story Is the Gap Between Prestige and Production

There are two LLM rankings that matter, and right now they are telling different stories. Arena AI's Text leaderboard — the one benchmark that developers actually trust — is basically a frozen lake this week. Anthropic holds four of the top five positions. Claude Opus 4.7 Thinking sits at

28 Apr 2026 4 min read

OpenClaw's Latest SSRF CVE Is a Useful Architectural Tell, Not Just Another Bug Fix

OpenClaw's Latest SSRF CVE Is a Useful Architectural Tell, Not Just Another Bug Fix

Here is the thing about server-side request forgery in an agent framework: it is never just about fetching a URL. It is about the gap between what a configuration interface thinks it is doing and what the runtime actually executes. CVE-2026-35629 landed this week with a CVSS v3.1 score

27 Apr 2026 4 min read

NVIDIA's NemoClaw Is the Industry's Best Argument That Agent Security Belongs in Infrastructure, Not Prompting

NVIDIA's NemoClaw Is the Industry's Best Argument That Agent Security Belongs in Infrastructure, Not Prompting

There is a quiet argument happening inside every team that puts an AI agent on a server and gives it access to things. It goes like this: the agent can read your emails, post to Slack, push to GitHub, and run commands on your network. That is the product. But

27 Apr 2026 5 min read

David Silver's .1B Raise Is the DeepMind Alumni Network Going Independent at Scale

David Silver left DeepMind and raised $1.1 billion at a $5.1 billion valuation. The headline writes itself. The interesting question is what exactly he is building — and why so many smart investors decided the answer was worth more than the GDP of a small country before a single

27 Apr 2026 4 min read

DeepMind's Korea Deal Is Google's Bet That National AI Partnerships Are Infrastructure, Not Theater

DeepMind's Korea Deal Is Google's Bet That National AI Partnerships Are Infrastructure, Not Theater

There is a version of this story that reads like a diplomatic press release: Google DeepMind, South Korea, ten-year AlphaGo anniversary, everyone smiles for the cameras. That version is true. It is also useless. The more interesting read is what a national AI partnership actually means when a frontier lab

27 Apr 2026 4 min read

Codex CLI 0.125.0 Is OpenAI Investing in the Control Plane, Not the Demo Layer

Codex CLI 0.125.0 shipped this week with a release note that is long on operational specifics and short on keynote energy. That is the point. OpenAI spent this release on app-server transport, thread persistence, permission-state consistency, rollout tracing, plugin management, and reliability around long-lived sessions. It is not

27 Apr 2026 3 min read

OpenAI's WebSocket Push Is Really a Bid to Remove the Agent Tax

There is a specific kind of frustration that sophisticated users of AI coding tools feel but rarely articulate cleanly: the model is fast, but the agent loop is slow. Not because the inference is sluggish, but because the overhead between turns compounds. API handshakes, context reconstruction, state validation, repeated authentication

27 Apr 2026 3 min read

GPT-5.5 Turns OpenAI's Coding Story Into a Workflow Story

There is a version of the GPT-5.5 launch story that is just benchmark theater: another model, another leaderboard nudge, another press release promising that this one is smarter. That version exists and you have seen it before. It is not the interesting version. The interesting version starts with a

27 Apr 2026 3 min read

OpenClaw’s New agent.capabilities Method Is a Small Feature with a Very Practical Thesis: Operators Need a Truthful Inventory

OpenClaw’s New agent.capabilities Method Is a Small Feature with a Very Practical Thesis: Operators Need a Truthful Inventory

One of the easiest ways to tell whether an agent platform is growing up is to look at the features that are too boring to trend. OpenClaw PR #72767, opened at 2026-04-27T10:55:04Z, adds a READ-scoped gateway method called agent.capabilities. On paper, it is just introspection: resolved primary

27 Apr 2026 4 min read

OpenClaw’s Latest Subagent Routing Fix Shows Multi-Agent Products Still Live or Die on Boring Return-Path Logic

OpenClaw’s Latest Subagent Routing Fix Shows Multi-Agent Products Still Live or Die on Boring Return-Path Logic

Multi-agent software is marketed like a cognition story. In production, it is much closer to a routing story. The impressive part is not that one agent can spawn another. The impressive part is whether the result comes back to the right human, in the right thread, under the right identity,

27 Apr 2026 4 min read

OpenClaw’s Discord Timeout Bug Is a Good Reminder That Partial Success Is Still Failure If the Control Plane Cannot Explain It

OpenClaw’s Discord Timeout Bug Is a Good Reminder That Partial Success Is Still Failure If the Control Plane Cannot Explain It

Agent platforms love to talk about autonomy. They should spend more time talking about outcome accounting. A system that performs useful work, keeps looking alive, and then tells the operator only that “something went wrong” has not merely produced an annoying edge case. It has failed at one of the

27 Apr 2026 4 min read

← Newer Posts Page 87 of 114 Older Posts →

The LGTM © 2026

Sign up

Powered by Ghost