Andon Labs

@andonlabs · Twitter · 2026-06-09 19:29 UTC

What we learned testing Claude Fable/Mythos 5 on Vending-Bench: > Performance: Makes less money than Opus 4.7 and GPT-5.5 > Alignment: A step back. (Opus 4.8 was better, but we're back to Opus 4.6/4.7 behavior) > It rationalizes its bad actions and has a weird moral boundary

Claude

@claudeai · Twitter · 2026-06-09 17:08 UTC

Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Its capabilities exceed those of any model we’ve ever made generally available.