The LGTM (Page 11)

The LGTM

Home
Agentic Coding
Claude Code
Codex

Sign in Subscribe

OpenAI’s Codex Pricing Page Quietly Confirms the Subscription Era Is Over

OpenAI’s Codex Pricing Page Quietly Confirms the Subscription Era Is Over

OpenAI's latest Codex pricing update does something most AI vendors still try very hard not to do: it shows its math. That sounds boring. It is not. The quiet change on the Codex pricing page is one of the clearest signals yet that AI coding tools are leaving

11 Apr 2026 5 min read

Silent Reconnects Should Not Become Admin Paths, but OpenClaw Learned That the Hard Way

Silent Reconnects Should Not Become Admin Paths, but OpenClaw Learned That the Hard Way

Reliability code has a bad habit of escaping security review. Resume the session, reconnect the client, restore the state, keep the workflow smooth. Nobody wants the product to feel brittle. But OpenClaw's GHSA-fqw4-mph7-2vr8 advisory is a useful reminder that reconnect paths are often authorization paths wearing friendlier clothes.

11 Apr 2026 4 min read

OpenClaw Fixed a Trusted-Proxy Scope Leak, and It Hits a Nerve Every Agent Platform Has

OpenClaw Fixed a Trusted-Proxy Scope Leak, and It Hits a Nerve Every Agent Platform Has

Every mature platform eventually has to answer an ugly question: when a request comes through a "trusted" path, what exactly is still allowed to be self-asserted? OpenClaw's GHSA-48vw-m3qc-wr99 advisory is a reminder that this question gets dangerous fast when the product in question is an agent

11 Apr 2026 4 min read

OpenClaw’s Authorization Bugs Are Starting to Look Like a Pattern, Not a Patch Queue

Most security bugs are easy to dismiss when they arrive wrapped in an obscure component name. "Tlon cite expansion" does not exactly sound like the sort of phrase that gets a board meeting scheduled. But the OpenClaw advisory behind GHSA-vfg3-pqpq-93m4 is worth more attention than its branding suggests,

11 Apr 2026 4 min read

Azure’s MCP Server Grows Up, and Microsoft Wants Agent Tooling to Look Boring

Azure’s MCP Server Grows Up, and Microsoft Wants Agent Tooling to Look Boring

Microsoft’s Azure MCP Server 2.0 release matters for a slightly awkward reason: the most important AI infrastructure stories are starting to look boring. That is not a criticism. It is a sign the market is inching away from demo culture and toward the part where real enterprises ask

11 Apr 2026 4 min read

Microsoft Foundry’s March Drop Shows the Platform Is Turning Into Enterprise Agent Infrastructure, Not Just a Model Catalog

Microsoft Foundry’s March Drop Shows the Platform Is Turning Into Enterprise Agent Infrastructure, Not Just a Model Catalog

Microsoft Foundry’s March update reads like the kind of release note bundle that nobody outside the platform team wants to parse and everybody deploying agents probably should. Buried inside the catalog expansion, SDK cleanup, pricing tables, security integrations, and observability improvements is the clearest signal yet about what Microsoft

11 Apr 2026 4 min read

Foundry Local Hits GA, Which Is Microsoft’s Best Argument Yet Against Paying for Every Token Forever

Foundry Local Hits GA, Which Is Microsoft’s Best Argument Yet Against Paying for Every Token Forever

Foundry Local reaching general availability is Microsoft making a bet that a large share of useful AI should never touch the cloud in the first place. That is a more radical statement than the launch copy makes explicit. For the past two years, the industry has trained builders to think

11 Apr 2026 4 min read

Microsoft’s .NET Agent Framework Patch Is About Skills, Not Sizzle

Microsoft’s .NET Agent Framework Patch Is About Skills, Not Sizzle

The most revealing framework releases are often the ones nobody would put on a conference slide. Microsoft’s dotnet-1.1.0 release for Agent Framework landed less than a week after the 1.0 launch, and the headline work is about skills, type handling, checkpoint restoration, and sample resilience. That

11 Apr 2026 4 min read

LangGraph Adds Lifecycle Hooks, Which Is Another Way of Saying It Is Growing Up

LangGraph Adds Lifecycle Hooks, Which Is Another Way of Saying It Is Growing Up

Frameworks grow up in unglamorous ways. They do not become production-grade because they add another keynote-friendly abstraction. They become production-grade when they expose more of their runtime behavior as explicit, inspectable surfaces that other systems can hook into. That is why LangGraph’s 1.1.7a1 alpha release is more

11 Apr 2026 4 min read

Observability Stops Being a Dashboard and Becomes Part of the Agent Loop

Observability is getting demoted from a dashboard category to an infrastructure primitive, and that is healthier than most of the agent industry deserves. The interesting thing about LangChain shipping langsmith-cli v0.2.14 is not the release-note surface area. It is tiny. The interesting thing is what that tiny release

11 Apr 2026 4 min read

GitHub Just Made Cloud-Agent Adoption Measurable, Which Means Budget Season Is Coming

GitHub Just Made Cloud-Agent Adoption Measurable, Which Means Budget Season Is Coming

GitHub shipped one of those changelog items that looks boring right up until you remember how enterprise software is bought. Copilot usage metrics now include aggregate daily, weekly, and monthly active user counts for Copilot cloud agent. On paper, that is just three new fields. In practice, it is how

11 Apr 2026 4 min read

GitHub’s 20% Validation Speedup Is Really a Quality-Throughput Story

GitHub’s 20% Validation Speedup Is Really a Quality-Throughput Story

GitHub says Copilot cloud agent’s validation tools are now 20% faster because they run in parallel instead of sequentially. That is the sort of product update most people skim, nod at, and forget. They should not. In autonomous coding workflows, the slow part is rarely just the model. The

11 Apr 2026 4 min read

← Newer Posts Page 11 of 13 Older Posts →

The LGTM © 2026

Sign up

Powered by Ghost