top | item 44409098 Vending-Bench: Testing long-term coherence in agents 3 points| andromaton | 8 months ago |andonlabs.com 1 comment order hn newest andromaton|8 months ago This is the same company behind Anthropic's Titanium cube vending fridge, recently on the front page. As of now, the leaderboard is #1 Claude 4 Opus #2 (distracted?) Human
andromaton|8 months ago This is the same company behind Anthropic's Titanium cube vending fridge, recently on the front page. As of now, the leaderboard is #1 Claude 4 Opus #2 (distracted?) Human
andromaton|8 months ago