The LGTM (Page 23)

The LGTM

Sign in Subscribe

QwenPaw 1.1.12 Beta Is Mostly Boring — Which Is Why It Matters

QwenPaw 1.1.12 Beta Is Mostly Boring — Which Is Why It Matters

QwenPaw v1.1.12-beta.1 is not the kind of release that produces a clean launch graphic. Good. The parts that make local agents useful rarely fit in a hero image. The beta is mostly a pile of operational fixes: isolated keychain master keys, a release verification gate, token and

Qwen-RobotWorld Is Alibaba’s Bet That Robots Need a Simulator in Their Head

Qwen-RobotWorld Is Alibaba’s Bet That Robots Need a Simulator in Their Head

Alibaba’s most interesting Qwen news this week is not another chat model. It is a model that tries to answer a harder question before a robot moves: what happens next? That is the useful way to read Qwen-RobotWorld, the new arXiv technical report from Alibaba’s Qwen team. The

OpenClaw Adds a Stream Stall Guard Because Agent Providers Sometimes Finish the Work and Forget to Say Done

OpenClaw Adds a Stream Stall Guard Because Agent Providers Sometimes Finish the Work and Forget to Say Done

OpenClaw PR #93640 is a reminder that “OpenAI-compatible” is not the same thing as operationally compatible. A provider can send every token the agent needs, include a finish_reason, record the request as successful on its dashboard, and still leave the client hanging forever because the stream never sends [DONE]

OpenClaw’s Kiro ACP Retry Fix Shows Why Multi-Agent Platforms Need Error Taxonomy, Not Hope

OpenClaw’s Kiro ACP Retry Fix Shows Why Multi-Agent Platforms Need Error Taxonomy, Not Hope

OpenClaw PR #93642 is a one-line regex-sized fix with a platform-sized lesson: multi-agent systems do not become reliable just because everyone agrees to speak the same protocol. Eventually a backend says “Internal error,” the thread keeps looking alive, and the orchestrator has to know whether that means “retry safely” or

NVIDIA SkillSpector Treats Agent Skills Like Supply-Chain Artifacts

NVIDIA SkillSpector Treats Agent Skills Like Supply-Chain Artifacts

Agent skills are starting to look less like helpful prompt folders and more like dependencies with a fake mustache. NVIDIA’s SkillSpector, updated today in its public GitHub repository, is useful precisely because it names the thing most coding-agent stacks have been politely avoiding: when you install a skill into