HN Explorer

anerli

↗ HN profile [ 68.8 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: Magnitude MCP – vision-first browser interaction for Claude Code (github.com)

    Hey HN - Anders and Tom here. We made a browser MCP using the same vision-first scaffolding as our SOTA (94% WebVoyager) browser agent Magnitude. This approach is more flexible and robust than DOM-based interactions and…

    2 points 0
  2. Pure-vision browser agent scores 94% on WebVoyager (SOTA) (github.com)
    5 points 1
  3. Show HN: Magnitude – Open-source AI browser automation framework (github.com)

    Hey HN, Anders and Tom here. We had a post about our AI test automation framework 2 months ago that got a decent amount of traction (https://news.ycombinator.com/item?id=43796003). We got some great feedback from the…

    134 points 41
  4. Parallel Scaling Law for Language Models (arxiv.org)
    2 points 1
  5. Show HN: Magnitude – open-source, AI-native test framework for web apps (github.com)

    Hey HN, Anders and Tom here - we’ve been building an end-to-end testing framework powered by visual LLM agents to replace traditional web testing. We know there's a lot of noise about different browser agents. If you've…

    179 points 44
  6. Can LLMs accurately evaluate their own confidence? (github.com)
    2 points 2
  7. Will AI Ruin Your Codebase? (magnitude.run)
    4 points 1
  8. Why LLM Agents Today Don't Work (langur.ai)
    2 points 0
  9. Show HN: Langur – consistent, observable LLM agents (github.com)

    Hi HN! I've been working on a new type of LLM agent framework designed with consistency and observability in mind. The agent behavior is represented as a directed graph, you can save/load agents, and the agent…

    1 points 0