The  LGTM
  • Home
  • Agentic Coding
  • Claude Code
  • Codex
Sign in Subscribe
oh-my-openagent’s Wakeup Fixes Show Agentic Coding Has a Harness Problem
agentic-coding

oh-my-openagent’s Wakeup Fixes Show Agentic Coding Has a Harness Problem

The most honest agentic-coding release notes are the ones that sound like incident reports. oh-my-openagent v4.1.1 does not promise a smarter model, a magical benchmark jump, or a new mascot with a suspiciously large context window. It fixes background wakeups, continuation hooks, synthetic resumes, and dangerous interactive shell
13 May 2026 5 min read
Copilot Code Review Adds Severity and Grouping Because AI Review Noise Is Now the Bottleneck
codex

Copilot Code Review Adds Severity and Grouping Because AI Review Noise Is Now the Bottleneck

GitHub’s latest Copilot code review change is not flashy. That is why it is worth paying attention to. Copilot review comments now carry High, Medium, and Low severity labels. Similar suggestions can be grouped together instead of repeated across a large pull request. Users opted into GitHub’s new
13 May 2026 6 min read
OpenAI’s Windows Sandbox Is the Codex Postmortem We Needed Before the Incident
codex

OpenAI’s Windows Sandbox Is the Codex Postmortem We Needed Before the Incident

OpenAI’s Windows sandbox writeup is the kind of security post the agent industry needs more of: detailed, awkward, and honest about the places where the first version was not enough. The headline is easy to undersell. “Codex now has a better Windows sandbox” sounds like platform plumbing, useful mostly
13 May 2026 5 min read
AgentMemory 0.9.11 Shows the Agent Plugin Format War Is Really About Portable Authority
openclaw

AgentMemory 0.9.11 Shows the Agent Plugin Format War Is Really About Portable Authority

AgentMemory 0.9.11 looks, at first glance, like a small integration release: a Codex plugin manifest, a marketplace entry, and a fix for an OpenClaw memory-slot bug. That undersells it. The release is a useful snapshot of where coding-agent infrastructure is going: memory, hooks, skills, MCP servers, and host
13 May 2026 5 min read
AnyFlow Is NVIDIA’s Argument That Video Diffusion Needs a Throttle, Not Just a Bigger Engine
nvidia

AnyFlow Is NVIDIA’s Argument That Video Diffusion Needs a Throttle, Not Just a Bigger Engine

Video-generation products do not need a sacred sampler setting. They need a throttle. That is the practical argument hiding inside NVIDIA’s new AnyFlow checkpoints on Hugging Face. AnyFlow is framed as an “any-step” video diffusion framework: a single distilled model should adapt to arbitrary inference budgets instead of being
13 May 2026 5 min read
NVIDIA’s Wan2.2 FP8/NVFP4 Checkpoints Are the Boring Part of Video AI That Actually Matters
nvidia

NVIDIA’s Wan2.2 FP8/NVFP4 Checkpoints Are the Boring Part of Video AI That Actually Matters

The least glamorous part of generative video is becoming the part that matters: not whether the demo clip looks impressive, but whether the model can be served, measured, rolled back, and kept inside a cost envelope without turning every request into a GPU bonfire. NVIDIA’s new FP8 and NVFP4
13 May 2026 5 min read
Copilot Cowork Gets Plugins, Mobile, Agent 365 Controls, and Claude Opus 4.7. Translation: Microsoft Wants Agents to Do Work, Not Just Chat About It.
azure-ai

Copilot Cowork Gets Plugins, Mobile, Agent 365 Controls, and Claude Opus 4.7. Translation: Microsoft Wants Agents to Do Work, Not Just Chat About It.

Microsoft’s Copilot Cowork update is easy to misread as a feature bundle: plugins, partner integrations, Fabric IQ, Dynamics 365 workflows, mobile support, Agent 365 controls, and Claude Opus 4.7. The more useful read is sharper: Microsoft is trying to turn Copilot from a place where knowledge workers ask
13 May 2026 5 min read
Foundry Private Networking Is Not a Checkbox. It Is Part of the ML System.
azure-ai

Foundry Private Networking Is Not a Checkbox. It Is Part of the ML System.

Private networking in Microsoft Foundry sounds like the sort of infrastructure checkbox that gets delegated to the network team after the AI demo works. That is backwards. Once a Foundry workload uses private endpoints, managed virtual networks, private inference, RAG dependencies, Key Vault, Azure AI Search, storage, registries, and controlled
13 May 2026 5 min read
Microsoft and SAP Are Turning ERP Agents Into Cross-Stack Coworkers. That Is Useful, and Also a Governance Problem.
azure-ai

Microsoft and SAP Are Turning ERP Agents Into Cross-Stack Coworkers. That Is Useful, and Also a Governance Problem.

Enterprise AI becomes real the moment it leaves the chat box and starts touching the system of record. That is the useful way to read Microsoft and SAP’s Sapphire 2026 announcements: not as another “Copilot meets Joule” partner slide, but as a preview of ERP workflows where agents negotiate
13 May 2026 5 min read
Phoenix 15.7.0 Shows Agent Evaluation’s Two Hard Problems: Feedback and Injection Bugs
ai-frameworks

Phoenix 15.7.0 Shows Agent Evaluation’s Two Hard Problems: Feedback and Injection Bugs

Phoenix 15.7.0 is the kind of release that explains the agent-evaluation market better than a dozen framework comparison posts. On one side, Arize added richer feedback loops: trace-level user feedback annotations, expandable session-turn messages, and session-tagged identifiers for open and axial coding workflows. On the other side, it
13 May 2026 4 min read
Langfuse 3.174.0 Makes Agent Observability Look More Like Governance Than Dashboards
ai-frameworks

Langfuse 3.174.0 Makes Agent Observability Look More Like Governance Than Dashboards

Langfuse 3.174.0 is not the release you would pick for a launch video. Good. The agent ecosystem already has enough launch videos. What it needs now is evidence that observability vendors understand they are no longer selling prettier dashboards for prompts. They are becoming the place where agent
13 May 2026 4 min read
Pydantic AI 1.95.0 Turns Tool Search Into a First-Class Agent Primitive
ai-frameworks

Pydantic AI 1.95.0 Turns Tool Search Into a First-Class Agent Primitive

Pydantic AI’s latest release is easy to misread as another framework changelog: a few naming migrations, a provider feature, some instrumentation cleanup, a dependency note. That would miss the useful part. Version 1.95.0 is really about admitting a production truth most agent demos still dodge: once an
13 May 2026 4 min read
← Newer Posts Page 61 of 113 Older Posts →
The LGTM © 2026
  • Sign up
Powered by Ghost