The LGTM (Page 36)

The LGTM

Sign in Subscribe

Running Qwen Behind Claude Code Is the Local-Agent Wedge Alibaba Should Care About

Running Qwen Behind Claude Code Is the Local-Agent Wedge Alibaba Should Care About

The interesting part of the latest Qwen/Claude Code field guide is not that someone made a local model answer coding prompts. That stopped being novel somewhere around the third weekend everybody spent compiling llama.cpp. The useful part is more specific: a refreshed GitHub Gist shows what it actually

OpenClaw Subagents Reporting “Cancelled” While Still Running Is a Control-Plane Truthfulness Bug

OpenClaw Subagents Reporting “Cancelled” While Still Running Is a Control-Plane Truthfulness Bug

Multi-agent systems do not need cheerful status. They need truthful status. If work is waiting, say waiting. If it failed, say failed. If it was cancelled, reserve that word for actual cancellation. The moment an orchestration platform tells a user “Background task cancelled” while the subagent keeps running and eventually

OpenClaw’s `message_sending` Hook Bypass Is the Kind of Security Bug That Makes Extensions Look Safer Than They Are

OpenClaw’s `message_sending` Hook Bypass Is the Kind of Security Bug That Makes Extensions Look Safer Than They Are

A security hook that silently does not run is worse than no hook. No hook forces operators to be honest about the risk. A documented hook that appears installed, loaded, and available — while major delivery paths skip it — creates the kind of false confidence that gets secrets posted to channels

OpenClaw v2026.6.x Prompt Bloat Shows Why Agent Platforms Need Context Budgets, Not Just Bigger Models

OpenClaw v2026.6.x Prompt Bloat Shows Why Agent Platforms Need Context Budgets, Not Just Bigger Models

OpenClaw’s prompt-bloat report is a reminder that context windows are not RAM. You do not get to pour every tool description, channel hint, safety rule, UI affordance, and delegation policy into the front of a model run and call it “free” because the model advertises 128K tokens. The bill

OpenClaw’s WhatsApp ACP Binding Bug Is a Sandbox Boundary Problem, Not a Routing Inconvenience

The dangerous OpenClaw bug this morning is not that WhatsApp routing is awkward. Awkward routing is a support ticket. The reported failure in issue #92449 is sharper: a WhatsApp direct message can resolve to the intended agent ID while failing to materialize the configured ACP runtime, which means a conversation

SpaceX's IPO Makes xAI's Business Reality a Line Item

SpaceX’s IPO filing turns xAI from a vibe into a line item. That is useful, because vibes do not survive public-market arithmetic forever. Reuters’ latest breakdown of SpaceX’s numbers puts the combined Musk AI story in unusually concrete terms: a $75 billion IPO, a targeted $1.75 trillion

Canada's Grok Deepfake Ruling Is a Product-Infrastructure Warning

Canada’s privacy watchdog did not just hand xAI a legal problem. It handed every generative-media team a product-readiness checklist written in regulatory ink. The Office of the Privacy Commissioner of Canada said this week that X Corp. and xAI violated federal private-sector privacy law after Grok’s image-generation tools

LangChain 1.3.8 Tightens the Agent Harness Where Provider Drift Hurts

LangChain 1.3.8 Tightens the Agent Harness Where Provider Drift Hurts

LangChain 1.3.8 is a maintenance release, which is exactly why it is worth reading. The agent-framework market still rewards launch posts about new abstractions, new demos, and new diagrams showing boxes calling other boxes. But the production pain is usually lower in the stack: provider names drift, structured-output

OpenCode 1.17.4 Ships the Boring MCP Fixes Teams Actually Need

OpenCode 1.17.4 Ships the Boring MCP Fixes Teams Actually Need

OpenCode 1.17.4 is the kind of release that looks small until you have actually tried to run a coding agent against a messy repo with real tools, real credentials, and a model provider that does not quite behave like the last one. The changelog is not trying to

Codex Is No Longer Waiting for Claude Code Users to Wander Over

Codex Is No Longer Waiting for Claude Code Users to Wander Over

OpenAI just made the coding-agent market less polite. The most important line in the latest Codex changelog is not a benchmark claim, a new model, or another screenshot of an agent editing a repo while everyone pretends not to notice the diff is enormous. It is the new “Migrate to