Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

LEO

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 2

  1. NVIDIA NeMo Turns Agent Failures into Tests and Harness Fixes

    An NVIDIA Technical Blog tutorial demonstrates an agent optimization cycle: use NeMo Compass to identify problems in recorded traces, create evaluations with NeMo Eval Author, update the agent’s instructions or harness, and compare results on development and held-out tasks. The NemoClaw example uses Hermes Agent in an NVIDIA OpenShell sandbox with recorded traces from a fictional company. In a separate car-door design example, NVIDIA reports that adding validation for malformed tool calls reduced such calls from 142 to zero. The same example reportedly achieved a 28% relative improvement in the workflow’s overall evaluation score and 35% fewer tool calls per run across six tested scenarios, with no regressions reported elsewhere.

    NVIDIA Technical Blog · 🔥 0
  2. LiberAI launches Liber-0 world-action model for robot control

    LiberAI launched Liber-0, a world-action model pretrained on more than 2.2 million hours of human-experience data, including human videos, LiberSense Glove hand-motion data and robot data. The company says the model transfers human operation skills to robot embodiments. In LiberAI’s physical-robot tests, Liber-0 achieved a 36.0% overall success rate across 600 zero-shot trials on 60 GPT-6-generated tasks, without task-specific robot demonstrations. GPT-6 Astra recorded a 5% overall success rate on the same tasks and robot, with each task tested three times. Liber-0’s reported tasks included making bubble tea, organizing objects and operating drawers.

    DoNews · 🔥 0

Experience and discussion from the community

Share my LEO experienceAsk about LEO

saleor: GraphQL native, API-only platform for scalable composable commerce.

What problem it solves Saleor provides an API-first way to build and extend commerce backends without a monolithic plugin architecture or technology lock-in. Its GraphQL-only design gives developers a consistent interface for commerce data, workflows, and integrations. Key features GraphQL API-only architecture — The backend is accessed, configured, and extended through APIs, with GraphQL as its A…

github.comhttps://github.com/saleor/saleor

taste-skill: An Agent Skill that helps coding agents build professional company websites instead of generic landing pages.

What problem it solves Coding agents tend to assemble generic landing pages rather than distinctive company websites. The skill addresses this by fixing a page system (one section per screen, equal edges, one design system), dealing art direction such as palettes, type pairings and hero layouts, using real photographs, brand icons and product UI, and verifying the result in a real browser. Key fea…

github.comhttps://github.com/Leonxlnx/taste-skill