The Behavioral Layer
BriefingsMapAboutRSS
the open note's neighborhood · Full map ↗

Tag: evaluation

14 items with this tag.

  • Jul 10, 2026

    OSWorld

    • computer-use
    • agents
    • benchmark
    • evaluation
    • reliability
  • Jul 10, 2026

    Petri

    • alignment
    • auditing
    • agent-safety
    • evaluation
    • open-source
  • Jul 10, 2026

    WebArena

    • web-agents
    • benchmark
    • agents
    • evaluation
    • long-horizon
  • Jul 10, 2026

    Alignment Faking in Large Language Models

    • deception
    • alignment
    • evaluation
    • model-behavior
    • training
  • Jul 10, 2026

    Frontier Models are Capable of In-context Scheming

    • scheming
    • deception
    • agents
    • oversight
    • evaluation
  • Jul 10, 2026

    Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

    • deception
    • safety-training
    • backdoors
    • model-behavior
    • evaluation
  • Jul 10, 2026

    OpenAI Introduces Model Spec Evals

    • model-spec
    • evaluation
    • compliance
    • behavior-measurement
  • Jul 09, 2026

    Gemini 3 Pro Model Card

    • system-card
    • model-behavior
    • safety
    • frontier-safety
    • evaluation
  • Jun 24, 2026

    LLM-as-a-Judge

    • evaluation
    • llm-as-judge
    • scalability
    • bias
    • behavior
  • Jun 24, 2026

    Red Teaming

    • evaluation
    • red-teaming
    • adversarial
    • safety
    • behavior
  • Jun 24, 2026

    Claude Opus 4.8 System Card

    • system-card
    • model-behavior
    • safety
    • evaluation
    • transparency
  • Jun 24, 2026

    ST-WebAgentBench

    • evaluation
    • safety
    • trust
    • policy-compliance
    • web-agents
    • benchmark
  • Jun 24, 2026

    tau-bench

    • evaluation
    • reliability
    • agents
    • rule-following
    • benchmark
    • behavioral-contracts
  • Jun 24, 2026

    Language Models (Mostly) Know What They Know

    • calibration
    • confidence
    • disclosure
    • honesty
    • evaluation

The Behavioral Layer · How this site is made · RSS

© 2026 Joel Goldfoot