Anatoliy Kolodkin - The LGTM (Page 81)

The LGTM

Home
Agentic Coding
Claude Code
Codex

Sign in Subscribe

Anatoliy Kolodkin

Codex CLI 0.132.0 Is a Runtime Release, Not a Demo Reel

Codex CLI 0.132.0 Is a Runtime Release, Not a Demo Reel

Codex 0.132.0 is the kind of release that looks small from the outside and matters precisely because it sands the runtime seams users hit every day. OpenAI shipped Codex CLI 0.132.0, a release aimed at making Codex easier to operate from scripts, SDKs, remotes, and long-running

23 May 2026 4 min read

Semantic Issue Search Makes Copilot Chat a Triage Surface, Not Just a Question Box

Semantic Issue Search Makes Copilot Chat a Triage Surface, Not Just a Question Box

Issue search is becoming less like grep and more like triage infrastructure. That is good news, provided teams remember that semantic matching is a ranking system, not a source of truth. GitHub added semantic issue search to Copilot Chat on the web, letting users find, group, and analyze issues with

23 May 2026 3 min read

Copilot Usage Reports Get a Stable GitHub Domain, Which Is Boring Until Your Firewall Breaks Finance

Copilot Usage Reports Get a Stable GitHub Domain, Which Is Boring Until Your Firewall Breaks Finance

Nobody gets excited about download URLs until the monthly AI bill is due and the firewall has quietly blocked the report finance needed yesterday. GitHub migrated Copilot usage metrics report download links from Azure Front Door patterns to stable GitHub-owned domains. For GitHub.com customers, report links now use https:

23 May 2026 3 min read

Copilot Auto Model Selection Turns Model Choice Into a Routing Problem

Copilot Auto Model Selection Turns Model Choice Into a Routing Problem

The most important button in Copilot is no longer the prompt box. It is the routing layer deciding how much model to spend on the work in front of you. GitHub updated Copilot auto model selection in VS Code so “Auto” no longer just means availability fallback; it now evaluates

23 May 2026 4 min read

GitHub Open-Sources Copilot for Eclipse, and the Interesting Part Is the Agent Internals

GitHub Open-Sources Copilot for Eclipse, and the Interesting Part Is the Agent Internals

Open-sourcing an IDE plugin sounds like housekeeping until you realize the repo is a map of how a modern coding agent actually enters an enterprise workstation. GitHub has open-sourced the GitHub Copilot for Eclipse plugin under the MIT license, moving the code into the public microsoft/copilot-for-eclipse repository. The announcement

23 May 2026 5 min read

Control UI Token Pairing Shows the Cost of Security Fixes That Break Local Trust Paths

Control UI Token Pairing Shows the Cost of Security Fixes That Break Local Trust Paths

Security hardening is easy to applaud until it breaks the control surface people need to run the system. OpenClaw PR #85459 is a good example of that uncomfortable middle ground. It restores local Control UI and WebChat browser-origin pairing when the client has a valid gateway token, after a previous

22 May 2026 4 min read

OpenClaw Coalesces Provider Auth Rewarms Because Channel Latency Is a Runtime Bug

OpenClaw Coalesces Provider Auth Rewarms Because Channel Latency Is a Runtime Bug

Provider authentication rewarm sounds like the sort of phrase that belongs in a log line nobody reads. Then Telegram reactions start taking one to two minutes after a message, and suddenly backend housekeeping is the product. OpenClaw PR #85487 is a small gateway patch with a useful lesson: channel latency

22 May 2026 4 min read

Codex Compaction Recovery Turns a Stuck Preflight Into a Bounded Restart

Codex Compaction Recovery Turns a Stuck Preflight Into a Bounded Restart

Codex compaction is not a feature most users think about until it starts breaking the part they do care about: the next answer. That is why OpenClaw PR #85500 is more interesting than its small diff suggests. It turns a stuck native compaction preflight from an ambient runtime failure into

22 May 2026 4 min read

GB200 Scheduling Is Where AI Infrastructure Stops Pretending the Network Is Someone Else’s Problem

GB200 Scheduling Is Where AI Infrastructure Stops Pretending the Network Is Someone Else’s Problem

The least glamorous part of AI infrastructure is becoming the part that decides whether the expensive hardware was worth buying. NVIDIA’s latest GB200 NVL72 guidance is nominally about Slurm topology-aware scheduling, but the real message is sharper: at rack-scale Blackwell, you cannot treat GPUs as identical integers anymore. Placement

22 May 2026 5 min read

Synthetic Medical Images Are NVIDIA’s Most Practical Open Model Play This Week

Synthetic Medical Images Are NVIDIA’s Most Practical Open Model Play This Week

Synthetic medical data has spent years stuck between two unhelpful extremes: demos that look impressive in a slide deck, and clinical claims that arrive several validation steps too early. NVIDIA’s new NV-Generate-MR-Brain release is more interesting because it lives in the middle. It is not trying to convince anyone

22 May 2026 5 min read

Microsoft 365 Copilot’s Usage Report Finally Admits Agents Need Their Own Adoption Metrics

Microsoft 365 Copilot’s Usage Report Finally Admits Agents Need Their Own Adoption Metrics

Microsoft’s updated Copilot usage-report documentation is not a flashy AI announcement, which is exactly why it is worth paying attention to. The company is now foregrounding agent usage alongside the usual Microsoft 365 Copilot adoption numbers: enabled users, active users, prompt volume, app-level usage, Copilot Chat split between work

22 May 2026 4 min read

Foundry Model Router Is Turning Model Choice Into Policy

Foundry Model Router Is Turning Model Choice Into Policy

The least glamorous feature in Microsoft Foundry may be one of the most important: a router that decides which model should answer a prompt. That sounds like product-manager convenience until you run enough AI workloads in production. Then it becomes obvious that “let every developer pick a model” is not

22 May 2026 4 min read

← Newer Posts Page 81 of 140 Older Posts →

The LGTM © 2026

Sign up

Powered by Ghost