The  LGTM
  • Home
  • Agentic Coding
  • Claude Code
  • Codex
Sign in Subscribe
Pydantic AI 1.94.0 Fixes the OpenAI-Compatible Lie Hiding in Agent Portability
ai-frameworks

Pydantic AI 1.94.0 Fixes the OpenAI-Compatible Lie Hiding in Agent Portability

“OpenAI-compatible” has become one of the most useful lies in AI infrastructure. Useful, because it gave local models, hosted inference providers, enterprise gateways, and framework authors a common shape to build around. A lie, because anyone who has tried to move a real agent from OpenAI’s API to a
12 May 2026 4 min read
CodeBurn Turns AI Coding Spend Into an Engineering Metric
agentic-coding

CodeBurn Turns AI Coding Spend Into an Engineering Metric

The least glamorous question in agentic coding is becoming the most important one: where did the tokens go? Not “which model is smartest,” not “which CLI has the best demo,” and definitely not “how many vibes did we ship this sprint.” The useful question is whether an AI coding session
12 May 2026 5 min read
Codex Auto-review Moves Approval Fatigue Into Policy
agentic-coding

Codex Auto-review Moves Approval Fatigue Into Policy

Approval prompts are the place where agent safety usually goes to die. Not because developers are reckless, but because repetitive permission dialogs train people to stop reading. If Codex asks for approval every time it needs to run a slightly privileged command, fetch a package, touch a neighboring directory, or
12 May 2026 5 min read
The Android Show Is Google Giving Android Its Own Runway Before Gemini Eats the Keynote
google-ai

The Android Show Is Google Giving Android Its Own Runway Before Gemini Eats the Keynote

The Android Show is Google admitting it has a keynote bandwidth problem. Android is too large to be the warm-up act, but Gemini is now too central to share the stage quietly. So Google is giving Android its own pre-I/O runway on May 12 before the main Google I/
12 May 2026 5 min read
llm-rankings

The LLM Leaderboard Has Split in Two

The most useful LLM leaderboard this week is not the one with the cleanest Elo score. It is the one where agents are quietly burning trillions of tokens. Arena AI’s text and WebDev/Code boards are stable enough to look almost boring: Anthropic still owns the top end, Claude
12 May 2026 5 min read
Codex Plugin Sharing and Copilot Managed Plugins Point to the Same Future: Agent Config Is Supply Chain
codex

Codex Plugin Sharing and Copilot Managed Plugins Point to the Same Future: Agent Config Is Supply Chain

Agent plugins are being marketed as convenience. That undersells them and, more importantly, under-threat-models them. A plugin for a coding agent is not a theme, a snippet pack, or a harmless preference bundle. It can carry instructions, skills, hooks, app integrations, MCP servers, and policy-shaped defaults. In other words: it
12 May 2026 4 min read
GitHub Copilot CLI’s /autopilot Update Is Small, but the Runtime Signals Are Not
codex

GitHub Copilot CLI’s /autopilot Update Is Small, but the Runtime Signals Are Not

GitHub Copilot CLI v1.0.45 has the kind of release notes that look small if you read them as feature bullets and much larger if you read them as runtime plumbing. A new /autopilot command is the easy headline. The more important story is everything around it: OpenTelemetry alignment,
12 May 2026 4 min read
OpenClaw’s Codex Onboarding Fix Is Really About App-Server Lifecycle Hygiene
openclaw

OpenClaw’s Codex Onboarding Fix Is Really About App-Server Lifecycle Hygiene

The Codex onboarding fix merged into OpenClaw today is tiny in code and large in meaning. openclaw onboard could reach “Onboarding complete” and then refuse to exit because migration discovery left a spawned codex app-server --listen stdio:// child attached to the Node.js process. The fix routes the probe through
11 May 2026 4 min read
OpenClaw’s Idle Gateway Stalls Show Why Agent Observability Has to Include the Event Loop
openclaw

OpenClaw’s Idle Gateway Stalls Show Why Agent Observability Has to Include the Event Loop

The most useful OpenClaw issue today is not a flashy model bug. It is a boring runtime report about an “idle” gateway that blocks its Node.js event loop for 8 to 12 seconds every 30 minutes. That is exactly the kind of failure agent platforms need to get better
11 May 2026 4 min read
openclaw

OpenClaw’s Claude CLI Bridge Has a Permission-Prompt Deadlock, Not a Model Problem

The Claude CLI bug filed against OpenClaw this morning is the kind of failure that gets misdiagnosed as “the model hung” until someone reads the wire protocol. Claude is not the interesting culprit here. The interesting culprit is a bridge that asked Claude CLI to run in live stream-json mode,
11 May 2026 4 min read
Jensen Huang’s Commencement Pitch Is NVIDIA’s AI Strategy in Graduation Robes
nvidia

Jensen Huang’s Commencement Pitch Is NVIDIA’s AI Strategy in Graduation Robes

Jensen Huang’s Carnegie Mellon commencement speech was dressed as advice to graduates, but it read like NVIDIA’s current strategy memo with a cap and gown on. The NVIDIA CEO told CMU’s 128th graduating class that they are entering “the beginning of the AI revolution,” that “a new
11 May 2026 5 min read
CUDA Python 1.0 Makes Python a First-Class Control Plane for Serious GPU Work
nvidia

CUDA Python 1.0 Makes Python a First-Class Control Plane for Serious GPU Work

CUDA Python 1.0 is not the sort of release that gets a launch keynote, which is precisely why it matters. NVIDIA shipped cuda-core 1.0.0 on May 11 as the first stable release of its Pythonic CUDA core API, complete with Semantic Versioning guarantees, deprecation periods, and a
11 May 2026 5 min read
← Newer Posts Page 64 of 113 Older Posts →
The LGTM © 2026
  • Sign up
Powered by Ghost