Nathan Lambert @natolambert

Whenever I see a model top this chart, it's normally a bit of a red flag. Would love to be proven wrong! [引用 @synthwavedd]: As expected, unfortunately the only bad thing about the new Opus is it's a token-gobbling monster. Uses the most tokens per Intelligence Index task of any model benchmarked. The price cut makes more sense here! https://t.co/igvjTkG0CP

X40 d ago
Read original ↗