Güncel topluluk tahmini
Before 2035-01-01 97.1%7 seçenek arasında lider
Before 2035-01-01 97.1%Tahminciler
26
Soru türü
multiple choice
Yöntem
Play-money forecasting platform
Kaynak türü
Tahmin
7g Değişim
0.0 pts
Piyasa verileri
15 saat önce güncellendi
Guncelligini yitirmis21 Şub 24 04:36 UTC2 Oca 36 07:59 UTC
Trendler
İlgili Piyasalar
Bağlam için ilgili sorular; eşdeğer sözleşmelerin karşılaştırması değildir.
By 2028, AI can perform as well as the best human entrants in the Putnam competition.
Manifold MarketsBy 2029, AI can provide phone banking services as well as human operators, without annoying customers more than humans?
Manifold MarketsBy 2030, Humanoid Robots can Fold laundry as well and as fast as the median human clothing store employee.
Manifold Markets[Carlini questions] Chance off-the-shelf AI system can play as well as casual player on arbitrary board game given rules
Manifold MarketsWhich company has best AI model end of 2026?
PolymarketBest AI at the end of 2026?
KalshiKurallar
The GAIA benchmark (https://arxiv.org/abs/2311.12983) aims to test for the next level of capability for AI agents.
- Quoting from the paper: "GAIA proposes real-world questions that require a set of fundamental abilities such as reasoning, multi-modality handling, web browsing, and generally tool-use proficiency.
- GAIA questions are conceptually simple for humans yet challenging for most advanced AIs: we show that human respondents obtain 92% vs. 15% for GPT-4 equipped with plugins."
- This market will resolve based on when an AI system performs as well or better than humans on all 3 of the different levels of the benchmark.
- I'll use the numbers from Table 4 in paper: 93.9% on level 1, 91.8% on level 2, and 87.3% on level 3.
- (I'm using the conjunction of all 3 levels rather than the average to be somewhat conservative about this level being achieved.)