The LGTM (Page 58)

The LGTM

Sign in Subscribe

NemoClaw + Hermes Is the Interesting Agent Demo Because the Policy Is Code, Not Vibes

NemoClaw + Hermes Is the Interesting Agent Demo Because the Policy Is Code, Not Vibes

The most important part of NVIDIA’s latest agent demo is not the agent. That sounds like a cheap trick, but it is the cleanest read on NVIDIA’s new developer walkthrough for running Nous Research’s Hermes Agent inside NemoClaw and OpenShell. The demo can read Outlook or Slack,

xAI’s Smart Turn Update Is About Voice-Agent UX, Not Just Transcription

xAI’s Smart Turn Update Is About Voice-Agent UX, Not Just Transcription

The least glamorous part of a voice agent is also the part users judge first: does it know when you are done talking? xAI’s June 2 documentation refresh adds Smart Turn support to streaming Speech-to-Text and image-search support to Grok’s Web Search tool. That will not trend like

AdaCodec Treats Video Tokens Like a Codec Problem, Not a Bigger Context Window Problem

AdaCodec Treats Video Tokens Like a Codec Problem, Not a Bigger Context Window Problem

Video multimodal models have a token accounting problem, and AdaCodec is refreshing because it says the quiet part plainly. A lot of video MLLM pipelines still behave as if every sampled frame deserves a full visual-token invoice. That is a strange habit for an industry that has spent decades learning

SubFit Says the Layer Is the Wrong Unit of LLM Compression

SubFit Says the Layer Is the Wrong Unit of LLM Compression

LLM compression keeps getting marketed as a storage problem. SubFit is a useful corrective because it treats compression as what it actually is in production: an inference-shape problem. The question is not merely whether you can make a checkpoint smaller. The question is whether the compressed model serves faster, uses

OpenAI Is Positioning Codex as a Multi-Agent Engineering Platform, Not a Better Autocomplete

OpenAI is no longer selling Codex as a smarter autocomplete box. The refreshed pitch is more ambitious, and more operationally awkward: Codex is becoming a command center for engineering work that can happen locally, in editors, in cloud environments, in parallel worktrees, through skills, through automations, and eventually across the