Alex Xi's Notes

Tag: evals

9 items with this tag.

  • Jul 06, 2026

    tweet-arc-agi-3-announcement

    • benchmarks
    • agi
    • evals
    • arc
  • Jul 06, 2026

    tweet-metr-gpt5-horizon

    • evals
    • metr
    • task-horizon
    • gpt-5
    • benchmarks
    • agents
  • Jul 06, 2026

    metr-measuring-ai-long-tasks

    • evals
    • agents
    • autonomous-research
    • scaling
  • Jul 06, 2026

    openai-real-world-tasks

    • evals
    • benchmarks
    • real-world
    • openai
  • Jul 06, 2026

    thoughts-on-evals

    • evals
    • agents
    • measurement
    • evaluation
  • Jul 06, 2026

    meta-harness-automatic-optimization

    • agents
    • harness
    • optimization
    • context
    • evals
  • Jul 06, 2026

    anthropic-ai-resistant-evals

    • evals
    • hiring
    • ai-resistant
    • anthropic
  • Jul 06, 2026

    anthropic-demystifying-evals

    • evals
    • agents
    • safety
    • anthropic
  • Jul 06, 2026

    cursor-bench-internal-eval

    • cursor
    • benchmarks
    • evals
    • coding-agents