Anatoliy Kolodkin - The LGTM (Page 38)

The LGTM

Sign in Subscribe

Anatoliy Kolodkin

Qwen's Bebop Paper Says the Expensive Part of Reasoning RL Is the Rollout Loop — and Then Makes It 1.8× Faster

Qwen's Bebop Paper Says the Expensive Part of Reasoning RL Is the Rollout Loop — and Then Makes It 1.8× Faster

Qwen’s Bebop paper is the kind of model news that does not look like model news because there is no shiny chat UI attached. That is a mistake. The visible model is only the artifact. The training loop is where the advantage compounds. The paper, Breaking Entropy Bounds: Accelerating

Codex 0.140 Alpha Shows OpenAI Building the Agent Runtime Around Context, Plugins, and Imports.

Codex 0.140 Alpha Shows OpenAI Building the Agent Runtime Around Context, Plugins, and Imports.

OpenAI’s latest Codex alpha is not a feature announcement. It is a map of what a serious coding-agent runtime has to become once the demo phase is over. Codex 0.140.0-alpha.8 was published on June 11 at 06:12:14 UTC, according to the GitHub Releases API.

Copilot CLI Gets /security-review. Treat It as a Fast First Pass, Not a Security Program.

Copilot CLI Gets /security-review. Treat It as a Fast First Pass, Not a Security Program.

GitHub just put a security reviewer in the terminal. That is useful. It is also exactly the sort of feature teams will misuse if they are desperate for a checkbox. Copilot CLI now has an experimental /security-review command for reviewing local code changes before they reach a pull request. GitHub

Copilot Chat Finally Gets Agent Memory. Now Teams Need Session Hygiene.

Copilot Chat Finally Gets Agent Memory. Now Teams Need Session Hygiene.

Copilot cloud agent just became harder to ignore, which is both the point and the problem. GitHub has updated Copilot Chat on the web so it can see the status of Copilot cloud agent sessions, answer questions about completed sessions, retrieve agent logs, and search past sessions by topic, title,

Claude Code 2.1.172 Is the Nested-Agent Release Hiding in a Bugfix Train

Claude Code 2.1.172 Is the Nested-Agent Release Hiding in a Bugfix Train

Claude Code v2.1.172 looks, at first glance, like another dense maintenance release in a product that now ships faster than most teams can update their internal docs. The headline is easy to miss: sub-agents can now spawn their own sub-agents, up to five levels deep. That is not

OpenClaw v2026.6.6-beta.1 Is a Security Release Wearing a Platform Release Jacket

OpenClaw v2026.6.6-beta.1 Is a Security Release Wearing a Platform Release Jacket

OpenClaw’s latest beta is easy to misread if you skim the changelog for the usual release-note dopamine: new providers, channel fixes, startup speed, better browser plumbing. Those are there. But the release’s center of gravity is much less glamorous and much more important: OpenClaw is hardening the seams

TacticAI Comes to Brazil: How Google DeepMind's Football AI Ended Up Inside Palmeiras' Training Room

TacticAI Comes to Brazil: How Google DeepMind's Football AI Ended Up Inside Palmeiras' Training Room

When Google announced that TacticAI — the football tactics assistant it built with Liverpool FC — was coming to Brazil, the press coverage read like a victory lap. Palmeiras, Brazil's biggest club by revenue, and the CBF, Brazilian football's governing body, both signed on to use Google'