Skip to content

Update README.md #17

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jennyf19 merged 1 commit into from
Jul 6, 2026
Merged

Update README.md #17

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 5 additions & 6 deletions agent-signals/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -332,12 +332,11 @@ actually verify — even on the runs where the agent never got to speak.
Frontier model providers are shipping architectures that separate capability
from verification.

Anthropic's Claude Fable 5 and Mythos 5 (2026) expose the same base model
through two tiers: a generally-available tier (Fable 5) with external safety
classifiers that intercept high-risk requests and route them to a fallback
model, and a restricted tier (Mythos 5) without those classifiers, available
only to vetted partners. The two tiers differ not in capability but in the
safeguards and vetting applied around access.
Anthropic's recent Claude Fable 5 and Mythos 5 release ships the same
underlying model through two different access tiers: a generally-available
tier with additional safeguards around high-risk requests, and a restricted
tier available only to vetted partners. Access is gated by verification and
vetting, not by raw capability.
Comment on lines +335 to +339

We read this as consistent with the premise behind Agent Signals: capability
alone isn't the thing to manage — verification is. Access-tiering addresses
Expand Down