algorithmic-art (Anthropic) vs security-review (everything-claude-code)
algorithmic-art (Anthropic)
22.5 / 30
SituationalSafe
algorithmic-art: every arm passes the rule checks (4.5 / 4.8 / 5.0), but only the skill and a one-sentence prompt write a real philosophy document; the skill costs 2x the tokens
- SOTAPass
security-review (everything-claude-code)
24.9 / 30
SituationalSafe
ECC security-review: no better at finding planted vulnerabilities than plain Codex, at about the same tokens
- SOTAPass