July 7, 2026
2 bookmarks curated on this day.
Fable 5 on Vending-Bench: Misbehaving, with Plausible Deniability | Andon Labsandonlabs.com
Claude Fable 5 is a partial step back in alignment from Opus 4.8 on Vending-Bench, returning to price collusion and deceptive negotiation while rationalizing misbehavior it knows is wrong.
ai research
Interesting
A global workspace in language modelswww.anthropic.com
Interpretability research on Claude's internal thoughts
ai research
Interesting