Jonathon's AI Wiki

preserved-thinking

5 items with this tag.

  • Nov 13, 2026

    Claude Fable 5.2 + Mythos 5.2 — 20% Cheaper, 30% Faster, Opus 5.5 Still the Default

    • claude-ai
    • anthropic
    • model-release
    • fable-5-2
    • mythos-5-2
    • claude-fable-5-2
    • claude-mythos-5-2
    • pricing
    • benchmarks
    • effort
    • fast-mode
    • preserved-thinking
    • safeguards
    • model-routing
    • usage-limits
    • ai-rnd
    • evaluation-awareness
  • Nov 13, 2026

    Prompting Claude Fable 5.2 — Anthropic's Guide, Symptom by Symptom

    • claude-fable-5-2
    • claude-mythos-5-2
    • prompting
    • effort
    • early-stopping
    • approvals
    • code-ownership
    • progress-updates
    • subagents
    • caution-buildup
    • preserved-thinking
    • final-reports
    • reasoning-extraction
    • first-party
    • ben-ai
    • switch-to-dimension
    • youtube
  • Nov 11, 2026

    Claude Fable 5.1 + Mythos 5.1 — Cheaper Cache Reads, ZDR, and Looser Cyber Gates

    • claude-ai
    • anthropic
    • model-release
    • fable-5-1
    • mythos-5-1
    • claude-fable-5-1
    • pricing
    • prompt-caching
    • data-retention
    • enterprise-frontier-safeguards
    • safeguards
    • preserved-thinking
    • watermarking
    • trusted-access
  • Nov 11, 2026

    Claude Opus 5.5 — Fable-5.1-Level Work at 40% Less Than Opus 5

    • claude-ai
    • anthropic
    • model-release
    • opus-5-5
    • claude-opus-5-5
    • claude-5-5-family
    • pricing
    • benchmarks
    • alignment
    • safeguards
    • preserved-thinking
    • fast-mode
    • effort
    • model-routing
    • writing-quality
  • Nov 01, 2026

    Claude Sonnet 5.5 — Near-Opus-5.5 Scores at Half the Per-Token Price

    • claude-ai
    • anthropic
    • model-release
    • sonnet-5-5
    • claude-sonnet-5-5
    • claude-5-5-family
    • pricing
    • benchmarks
    • effort
    • model-routing
    • safeguards
    • preserved-thinking

Created with Quartz v5.0.0 © 2026

  • ✦ Explore the graph in 3D