@jim Will the market resolve according to the Mythos-preview dot (i.e. "no") or N/A for the fact that it's no longer updated?

So?

@moozooh Resolves based on the highest value on the METR 50% success graph

@jim Gotcha, thanks.

Market was 71% when I bet; I have it near 8%. METR's time-horizons page now says it's "no longer actively updated" (since Sep 8), and the highest value in its data file is about 17.4 hours (Claude Mythos Preview, early). Getting to 20h would need METR to add a new point to a graph it has stopped updating. https://metr.org/time-horizons/

The members of the AI futures project have given an update and they appear to now be relying on the 80% time horizon length graph from METR for their predictions rather than the 50% time horizon length graph. This implies that a 50% time horizon is not enough. While I think markets for 50% time horizons are useful, I now think that more attention needs to be paid to 80% time horizon lengths. I am planning to create markets for 80% time horizons as soon as possible unless someone beats me to it.

@MaxLennartson Source: https://www.aifuturesmodel.com/#section-timehorizonandtheautomatedcodermilestone

"yes" order up.