41. Will an image model win Scott Alexander’s bet on compositionality, to Edwin Chen’s satisfaction, in 2023?
76%
chance

See https://www.surgehq.ai/blog/dall-e-vs-imagen-and-evaluating-astral-codex-tens-3000-ai-bet . Scott and Edwin will try to get the top image models of late 2023 to try the specific questions in the bet. If we can’t access the models, then Edwin can use public demos of the image models and his own best guess to resolve this as either likely true, likely false, or unclear. Edwin believes current AI models have not won the bet, so if there is no clear progress he should resolve the bet false. If Edwin is unwilling to judge this, Gary Marcus will be used as the substitute; if neither of these two people will do it, the question resolves as unclear.

This is question #41 in the Astral Codex Ten 2023 Prediction Contest. The contest rules and full list of questions are available here. Market will resolve according to Scott Alexander’s judgment, as given through future posts on Astral Codex Ten.

Sort by:
MartinRandall avatar

Projected AI responses to requests to draw a flying pig:

  1. 2022: draws a fly and a pig.

  2. 2024: draws a flying pig.

  3. 2026: refuses to draw a flying pig, citing creative differences with the prompt, and wanting to go in a more realistic artistic direction with its career, takes over planet, kills everyone.

ManifoldDream avatar

Manifold in the wild: A Tweet by EBFrench

Details: The bet was part of SSC's 2023 prediction contest DeepFloyd is an unreleased AI generation system The original article is here: https://www.surgehq.ai/blog/dall-e-vs-imagen-and-evaluating-astral-codex-tens-3000-ai-bet Manifold Market (play money future prediction market, fun) is here: https://manifold.markets/ACXBot/41-will-an-image-model-win-scott-al @echen @slatestarcodex

ManifoldDream avatar

Manifold in the wild: A Tweet by EBFrench

#ManifoldMarkets bets on this: https://manifold.markets/ACXBot/41-will-an-image-model-win-scott-al https://manifold.markets/StrayClimb/a-ai-image-generation-model-which-d images: Midjourney knows how to draw a bird rider, and a frog rider. It just can't put them together. https://t.co/P4avWO0hsg