The LGTM (Page 96)

The LGTM

Home
Agentic Coding
Claude Code
Codex

Sign in Subscribe

Microsoft Just Added an Open Agent Model to Foundry, but the Real Story Is the Pricing-Per-Autonomy Tradeoff

Microsoft did not just add another model to Foundry this week. It added a pricing argument. Kimi K2.6 arrives in Microsoft Foundry with the usual platform language about multimodality, coding, and agentic workflows, but the detail worth paying attention to is the one procurement teams will notice first: Microsoft

23 Apr 2026 4 min read

xAI's New Multi-Agent Mode Says Grok Wants to Be More Than a Loud Chatbot

xAI's New Multi-Agent Mode Says Grok Wants to Be More Than a Loud Chatbot

xAI's new multi-agent documentation matters for the same reason most multi-agent launches do not: it is specific enough to reveal the cost model, the orchestration model, and the product ambition all at once. The company quietly published a beta page for grok-4.20-multi-agent, and buried in that doc

23 Apr 2026 4 min read

xAI Quietly Shipped the Most Practical MCP Server in Its Stack

xAI Quietly Shipped the Most Practical MCP Server in Its Stack

xAI's most useful launch this week is not a new benchmark, a louder Grok personality trait, or another promise that the future belongs to agents. It is a documentation server. That sounds small until you notice what the company actually shipped: a hosted MCP endpoint at https://docs.

23 Apr 2026 4 min read

LazyAgent Is a Bet That the Next AI Coding Tool Is an Observability Layer, Not Another Agent

LazyAgent Is a Bet That the Next AI Coding Tool Is an Observability Layer, Not Another Agent

The most believable new tool in agentic coding this week is not another model, another shell, or another promise that the AI can now build your startup while you sleep. It is a terminal UI called lazyagent, and its premise is almost insultingly practical: once you have multiple coding agents,

23 Apr 2026 5 min read

OpenAI’s Axios Incident Is the Security Memo Every Coding-Agent Team Needed

OpenAI’s Axios incident is the kind of story that looks small if you read it like PR and large if you read it like infrastructure. On the surface, the company is saying the right calming things: no evidence of user-data exposure, no evidence of product compromise, no evidence that

23 Apr 2026 5 min read

The Real LLM Rankings Story Is What Developers Buy After Benchmarks Stop Moving

The interesting thing about LLM rankings right now is not who sits at the top. It is how little that answer changes, and how much buying behavior keeps moving anyway. April 22 delivered a clean version of that split. Arena's text leaderboard barely twitched. The top 20 stayed

23 Apr 2026 5 min read

GitHub Copilot for Jira Is Quietly Becoming a Policy Engine, Not Just a Ticket-to-PR Bridge

GitHub Copilot for Jira Is Quietly Becoming a Policy Engine, Not Just a Ticket-to-PR Bridge

GitHub’s newest Copilot-for-Jira update is the kind of release that gets ignored by people who only pay attention to model launches and benchmark screenshots. That is a mistake. The interesting thing here is not that GitHub added a few knobs to an integration. It is that GitHub is steadily

23 Apr 2026 5 min read

OpenAI Wants Codex to Stop Being a Personal Copilot and Start Being Team Infrastructure

OpenAI has spent the last year proving Codex can be useful to individual developers. This week it started making a different argument: usefulness is not enough. If Codex is going to matter inside companies, it has to stop behaving like a talented personal assistant and start behaving like team infrastructure.

23 Apr 2026 4 min read

Claude Code’s April 23 Release Keeps Pushing the Tool Downstack Into Workflow Infrastructure

Claude Code’s April 23 Release Keeps Pushing the Tool Downstack Into Workflow Infrastructure

Claude Code's April 23 release is the sort of update that looks minor if you read changelogs the way investors read press releases. No new frontier model. No sweeping platform launch. No benchmark screenshot war. What Anthropic actually shipped in v2.1.118 is something more consequential for

23 Apr 2026 5 min read

OpenClaw’s Bundled-Dependency Fix Solves One Packaging Problem and Immediately Runs Into the Real One: Sandboxes Hate Surprise Writes

OpenClaw’s Bundled-Dependency Fix Solves One Packaging Problem and Immediately Runs Into the Real One: Sandboxes Hate Surprise Writes

Packaging bugs are rarely glamorous, but they are where agent platforms meet reality. OpenClaw’s PR #70138, which eagerly installs bundled runtime dependencies for packaged installs, is a useful case study in how one sensible fix can immediately collide with a second, deeper constraint. Yes, packaged installs should not ship

22 Apr 2026 4 min read

OpenClaw’s Cache-Warmer Proposal Says the Quiet Part Out Loud: Prompt Caching Is Becoming Part of Agent Runtime Design

OpenClaw’s Cache-Warmer Proposal Says the Quiet Part Out Loud: Prompt Caching Is Becoming Part of Agent Runtime Design

Prompt caching is having the same career arc connection pooling had years ago. It starts life as a performance optimization people mention in docs and ends up becoming part of runtime design. OpenClaw’s cache-warmer proposal is interesting for exactly that reason. Issue #70418 is nominally about Anthropic prompt-cache TTLs,

22 Apr 2026 4 min read

OpenClaw’s 2026.4.21 Release Is Small on Paper, but It Quietly Tightens the Contract Around Images, Recovery, and Admin Power

OpenClaw’s 2026.4.21 Release Is Small on Paper, but It Quietly Tightens the Contract Around Images, Recovery, and Admin Power

Patch releases are where agent platforms reveal what they really think matters. Big launches get the applause, but the small releases tell you where the maintainers have found real pain in production. OpenClaw v2026.4.21 is one of those releases. On paper it is short: image-generation defaults move to

22 Apr 2026 4 min read

← Newer Posts Page 96 of 116 Older Posts →

The LGTM © 2026

Sign up

Powered by Ghost