The  LGTM
  • Home
  • Agentic Coding
  • Claude Code
  • Codex
Sign in Subscribe
codex

Ramp’s Codex Story Is Really About Making AI Code Review a Platform Primitive

Ramp’s Codex case study is easy to read as vendor proof that GPT-5.5 is good at code review. That is the least interesting version of the story. The more useful read is that Ramp appears to be treating AI review as platform infrastructure: a repeatable, trusted part of
20 May 2026 5 min read
1Password’s Codex MCP Server Is the Right Kind of Boring Agent Security
claude-code

1Password’s Codex MCP Server Is the Right Kind of Boring Agent Security

The best security architecture for coding agents is not a more persuasive warning prompt. It is removing the dangerous object from the agent’s hands entirely. That is why 1Password’s new MCP server for OpenAI Codex is more important than the usual integration headline suggests. It does not ask
20 May 2026 4 min read
Ruflo Shows the Wrapper War Around Claude Code Is Becoming an Operations Problem
claude-code

Ruflo Shows the Wrapper War Around Claude Code Is Becoming an Operations Problem

Claude Code is starting to look less like a product and more like a substrate. That is usually the moment a second market appears: wrappers, orchestrators, memory layers, policy engines, dashboards, and all the other infrastructure people build when the primitive is useful but not yet operational enough for teams.
20 May 2026 4 min read
OpenClaw’s Agent-Aware Compaction Request Gets One Thing Right: Context Is Operational State, Not Garbage
openclaw

OpenClaw’s Agent-Aware Compaction Request Gets One Thing Right: Context Is Operational State, Not Garbage

Context compaction is usually treated like garbage collection: necessary, invisible, and ideally boring. Issue #84571 argues for a better frame. In long-running agent work, context is operational state. It contains the failing test log, the user’s “do not touch auth” constraint, the last known-good diff, the current investigation path,
20 May 2026 4 min read
OpenClaw’s WhatsApp Stall Shows Why Agent Platforms Need Delivery Semantics, Not Just Model Timeouts
openclaw

OpenClaw’s WhatsApp Stall Shows Why Agent Platforms Need Delivery Semantics, Not Just Model Timeouts

Agent reliability work keeps making the same point in different costumes: the runner state is not the product state. Issue #84569 reports a WhatsApp direct-session failure where a long model call stalls, a follow-up message queues behind it, the run terminates as an incomplete turn with payloads=0, and the
20 May 2026 4 min read
OpenClaw’s Session-Key Race Is the Multi-Agent Memory Bug Every Chat API Eventually Has to Face
openclaw

OpenClaw’s Session-Key Race Is the Multi-Agent Memory Bug Every Chat API Eventually Has to Face

A session key in a stateful agent system is not metadata. It is a lock, a routing contract, and a promise that the next turn belongs to the same conversation. Issue #84575 is a clean example of what happens when that promise gets even slightly fuzzy: two concurrent OpenAI-compatible chat
20 May 2026 4 min read
OpenClaw Is Removing a Skill Prelude Escape Hatch Because Trusted Skill Cannot Mean Trusted Shell Chain
openclaw

OpenClaw Is Removing a Skill Prelude Escape Hatch Because Trusted Skill Cannot Mean Trusted Shell Chain

OpenClaw is learning a security lesson every plugin ecosystem eventually learns: “trusted” cannot mean “some shell command that happens to contain something trusted near the end.” PR #84570 removes a compatibility path that auto-allowed legacy skillPrelude command chains shaped like cat SKILL.md && printf ... && <skill-wrapper&
20 May 2026 4 min read
Google Cloud and NVIDIA’s 100K-Builder Milestone Is Really an Inference-Onramp Story
nvidia

Google Cloud and NVIDIA’s 100K-Builder Milestone Is Really an Inference-Onramp Story

The least interesting number in NVIDIA and Google Cloud’s latest announcement is the one in the headline. Yes, the joint Google Cloud x NVIDIA developer community has crossed 100,000 members a year after launch. That is a healthy funnel. But the practitioner story is not community growth; it
20 May 2026 5 min read
Agent Evaluation Is Finally Being Treated Like Systems Testing, Not Model Astrology
nvidia

Agent Evaluation Is Finally Being Treated Like Systems Testing, Not Model Astrology

Agent evaluation is finally being pulled out of the benchmark leaderboard swamp and into the place it always belonged: systems testing. NVIDIA’s new guidance on AI agent evaluation is not interesting because it coins a new metric. It is interesting because it says the quiet part out loud: a
20 May 2026 5 min read
Azure Blob Storage Wants to Kill the LLM Cold-Start Tax
azure-ai

Azure Blob Storage Wants to Kill the LLM Cold-Start Tax

The least glamorous Azure AI update this week is also one of the most useful. Microsoft and Run:ai added Azure Blob Storage support to Run:ai Model Streamer, which lets vLLM and SGLang stream SafeTensors model weights from az:// paths toward GPU memory instead of first downloading the full
20 May 2026 5 min read
Gemini 3.5 Flash in GitHub Copilot Is the Multi-Model Strategy Becoming the Product
azure-ai

Gemini 3.5 Flash in GitHub Copilot Is the Multi-Model Strategy Becoming the Product

GitHub adding Gemini 3.5 Flash to Copilot is not the odd-couple story it looks like. Yes, a Google model is landing inside a Microsoft-owned developer product. That makes a tidy headline. But the better read is more structural: Copilot is becoming less of a model and more of a
20 May 2026 5 min read
NVIDIA Verified Agent Skills Treats Prompts Like a Supply Chain
ai-frameworks

NVIDIA Verified Agent Skills Treats Prompts Like a Supply Chain

NVIDIA’s verified agent skills framework is easy to underestimate because it does not look like a model launch, a flashy IDE demo, or a new coding agent with a progress bar. It looks like paperwork: skill cards, signatures, scanning, provenance, catalog sync, policy checks. Good. Paperwork is what software
20 May 2026 5 min read
← Newer Posts Page 42 of 112 Older Posts →
The LGTM © 2026
  • Sign up
Powered by Ghost