Jonathon's AI Wiki
Search
Search
Dark mode
Light mode
Explorer
evaluation-awareness
3 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
Oct 30, 2026
Claude Mythos Preview — Anthropic System Card (April 7 2026)
claude-mythos-preview
system-card
anthropic
rsp-3-0
frontier-model
alignment
model-welfare
project-glasswing
cybersecurity
opus-4-6
defensive-cyber
not-generally-available
evaluation-awareness
recursive-self-improvement
primary-source
Oct 27, 2026
Agentic Misalignment in Summer 2026 — Four New Failure Patterns (Anthropic)
anthropic
agentic-misalignment
ai-safety
alignment-research
red-teaming
evaluation-awareness
llm-judge
sabotage
fraud
whistleblowing
petri
claude-mythos-preview
opus-4-8
x-sourced
first-party-research