Luckey Faraday
@luckeyfaraday
Exploring the AI frontier: models, agents, benchmarks & applied experiments. I test, compare and build. (kinda got DMCA'd by two companies we don't talk about)
加入 February 2024
183 正在關注 3.3K 粉絲
Haiku 5.5 vs. GPT-6 Luna.
Same Mario test. Same prompt.
Luna finished in 1m 03s for $0.014.
Haiku took 3m 32s for $0.037.
And the difference in the final result is pretty brutal.
顯示更多
