Will this Dan Mac tweet hold up?
2
1kṀ2540resolved Sep 29
Resolved
N/A1H
6H
1D
1W
1M
ALL
https://x.com/daniel_mac8/status/1972337371632013538
The claims that will be tested:
1. Anthropic release Sonnet 4.5 this week. (Before October 6th)
Tops SWE-Bench and Terminal-Bench
3 hour tasks on METR Long Duration
Price parity with GPT-5
If there's ambiguity, I will message Daniel and try to get clarification, but will resolve it fairly per my judgement.
This question is managed and resolved by Manifold.
Get
1,000 to start trading!
People are also trading
Sort by:
@ian Yeah, if the timing wasn't so close, I would have let this stand, but without time to speculate it's no fun.