The  LGTM
  • Home
  • Agentic Coding
  • Claude Code
  • Codex
Sign in Subscribe
Claude Cowork Moves the Agentic Coding Loop Onto the Desktop
agentic-coding

Claude Cowork Moves the Agentic Coding Loop Onto the Desktop

Claude Cowork is not Anthropic inventing “AI for office work.” That category has been over-announced, under-instrumented, and generally packaged as a nicer text box since 2023. The interesting part is narrower and more important: Anthropic is taking the agent loop that made Claude Code useful for developers and moving it
13 May 2026 5 min read
Googlebook Is the Chromebook Rewrite Google Could Only Ship After Gemini
google-ai

Googlebook Is the Chromebook Rewrite Google Could Only Ship After Gemini

Googlebook is what happens when Google looks at the Chromebook story and decides the browser is no longer enough of an operating thesis. Fifteen years ago, “cloud-first laptop” was a clean idea. In 2026, Google’s new pitch is more ambitious and messier: the laptop as an intelligence system, with
13 May 2026 5 min read
Gemini’s Smart Pointer Is a UI Primitive, Not a Cursor Gimmick
google-ai

Gemini’s Smart Pointer Is a UI Primitive, Not a Cursor Gimmick

The easiest way to dismiss Google DeepMind’s new AI pointer work is to call it Clippy with a cursor. That would be satisfying, briefly, and also wrong. The interesting part is not that Gemini can appear near your mouse. The interesting part is that Google is trying to make
13 May 2026 5 min read
Hy3 Is Turning Free Tokens Into Real Traffic
llm-rankings

Hy3 Is Turning Free Tokens Into Real Traffic

The LLM leaderboard story this week is not that a new model dethroned Claude. It did not. Arena AI’s Text and Code charts are basically frozen, with Anthropic still sitting on the top four Code slots and three of the top five Text slots. The more useful signal is
13 May 2026 5 min read
OpenAI Daybreak Turns Cyber AI Into a Security Workflow, Not a Scanner
ai-models

OpenAI Daybreak Turns Cyber AI Into a Security Workflow, Not a Scanner

OpenAI’s Daybreak announcement is short enough to look like a landing page. That is the wrong read. The interesting part is not the copy OpenAI published; it is the product shape hiding inside it: cyber-capable models are being moved out of the “ask a chatbot to audit this repo”
13 May 2026 5 min read
Codex Auto-Review Turns Approval Fatigue Into a Policy Problem — Which Is Exactly Where It Belongs
codex

Codex Auto-Review Turns Approval Fatigue Into a Policy Problem — Which Is Exactly Where It Belongs

Codex Auto-review is one of the least flashy and most important pieces of agent infrastructure OpenAI has documented lately. The feature does not promise a smarter model, a bigger context window, or another benchmark trophy. It attacks a more practical failure mode: if coding agents are useful enough to run
13 May 2026 5 min read
Codex Pricing Just Became Token Accounting — Which Means Agent Cost Is Now an Engineering Problem
codex

Codex Pricing Just Became Token Accounting — Which Means Agent Cost Is Now an Engineering Problem

OpenAI just made Codex pricing less mysterious and more annoying in exactly the way serious engineering teams should want. The new Codex rate card moves the conversation away from fuzzy “messages,” “tasks,” and “included usage” toward credits per million input tokens, cached input tokens, and output tokens. That is more
13 May 2026 5 min read
QwenPaw’s Beta Turns Memory Into the Next Agent Permissions Problem
qwen

QwenPaw’s Beta Turns Memory Into the Next Agent Permissions Problem

QwenPaw’s latest beta is not trying to win a screenshot contest. Good. The release is mostly memory plumbing, shell configuration, channel fixes, browser-tool batching, malformed tool-call filtering, plugin support, and session-routing cleanup — the kind of changelog that looks dull until you have actually tried to run an agent across
12 May 2026 5 min read
A Fresh OpenClaw Cron Bug Shows Why Agent Schedulers Need Lane Isolation, Not Just Health Checks
openclaw

A Fresh OpenClaw Cron Bug Shows Why Agent Schedulers Need Lane Isolation, Not Just Health Checks

The most useful OpenClaw bug reports are not the spectacular ones. They are the ones where everything looks healthy until a user notices the agent stopped behaving like an agent. GitHub issue #81234, opened just after 01:00 UTC on May 13, is one of those. After upgrading a beta
12 May 2026 5 min read
OpenClaw 2026.5.12-beta.3 Is a Permission-Boundary Release Wearing a Changelog Costume
openclaw

OpenClaw 2026.5.12-beta.3 Is a Permission-Boundary Release Wearing a Changelog Costume

OpenClaw’s latest beta is the kind of release that looks like a changelog avalanche until you squint at the shape of it. The shape is authority. Who gets to see which tools? Which agents are allowed to message outside their own context? Can uploaded skill archives enter the runtime
12 May 2026 5 min read
Microsoft’s Skills Repo Turns Agent Instructions Into Supply-Chain Code
ai-frameworks

Microsoft’s Skills Repo Turns Agent Instructions Into Supply-Chain Code

Microsoft’s microsoft/skills repository looks, at first glance, like another pile of helpful Markdown for coding agents. That is the least interesting way to read it. The better read is that Microsoft is treating agent context as an installable, versioned, reviewable artifact — and that means agent instructions are becoming
12 May 2026 4 min read
OpenAI Agents Python 0.17.2 Fixes the Runtime Edges Where Real Agents Break
ai-frameworks

OpenAI Agents Python 0.17.2 Fixes the Runtime Edges Where Real Agents Break

OpenAI Agents Python 0.17.2 is a patch release with almost no headline glamour, which is usually where the useful engineering signal hides. The fixes land around reasoning persistence, unknown realtime tools, tracing shutdown, approval rejection reasons, async SQLite session settings, and empty chat tool outputs. In other words:
12 May 2026 4 min read
← Newer Posts Page 62 of 113 Older Posts →
The LGTM © 2026
  • Sign up
Powered by Ghost