← Retour au fil
Anthropic’s new AI leads freelance benchmarks, yet fails 58% of the tasks
CryptoSlate12 nov., 21h · il y a 4j

Anthropic’s new AI leads freelance benchmarks, yet fails 58% of the tasks

Anthropic’s Fable 5.2 tops Scale’s Remote Labor Index at 41.3% but still fails 58.7% of freelance projects, with costs and human support unclear.

Détails

Source
CryptoSlate
Publication
12 nov. à 21h40

Contenu source (brut)

Anthropic’s new AI leads freelance benchmarks, yet fails 58% of the tasks. Anthropic’s Fable 5.2 tops Scale’s Remote Labor Index at 41.3% but still fails 58.7% of freelance projects, with costs and human support unclear.