Will tailcalled think that the Shard Theory alignment research program has achieved something important by October 20th, 2026?
One-OffIA1mManifold MarketsSem KYCDados de resolução verificadosRazoavelmente calibradoPrevisão da comunidade atualNão 88.2%
Previsores
25
Tipo de pergunta
binary
Metodologia
Play-money forecasting platform
Tipo de fonte
Previsão
Dados do mercado
Atualizado há 2 horas
Desatualizado20/10/22, 13:04 UTC20/10/26, 21:59 UTC
Tendências
Regras
The Shard Theory research program by Team Shard is based on the idea that we should directly study the what types of cognition/circuitry are encouraged by reinforcement learning, and reason mechanistically about how reward leads to them, rather than the classic Outer Alignment/Inner Alignment factorization which aims to create a reward function that matches human values and somehow give an AI a goal of maximizing that reward.
- A hope is that understanding how reward maps to behavior is more tractable than Outer Alignment/Inner Alignment, and that we therefore might be able to solve alignment without solving Outer Alignment/Inner Alignment.
- In 4 years, I will evaluate Shard Theory and decide whether there have been any important good results since today.
- I will probably ask some of the alignment researchers I most respect (such as John Wentworth or Steven Byrnes) for advice about the assessment, unless it is dead-obvious.
- About me: I have been following AI and alignment research on and off for years, and have a somewhat reasonable mathematical background to evaluate it.
- I tend to have an informal idea of the viability of various alignment proposals, though it's quite possible that idea might be wrong.
Mercados abertos
AI
KALSHITop AI model in September?
- claude-fable-5.1-max-12.0pt72%
- claude-opus-5-high+2.0pt6%
- claude-opus-4-6-thinking4%
+3 mais resultados
- Volume total
- € 135,2 mil
- Volume 24h
- € 102,7 mil
POLYMARKETWill CMI declare a Millennium Prize Problem solved by which date?
- 2028+6.5pt62.1%
- 2027-3.5pt28.4%
- 2026+2.0pt9.5%
POLYMARKETAnthropic IPO by which date?
- December 31,-1.0pt90%
- December 15,+3.5pt90%
- November 30,85%
+7 mais resultados
- Volume total
KALSHIBest AI at the end of 2026?
- Claude-0.7pt61.4%
- ChatGPT-2.1pt22.8%
- Grok-0.1pt7.9%
+5 mais resultados
- Volume total
- € 9,1 mi
KALSHIBest AI in Sep 2026?
- Claude+3.0pt81.3%
- ChatGPT-1.0pt11.2%
- Grok2.8%
+4 mais resultados
- Volume total
- € 325 mil
POLYMARKETOpenAI’s Astra Model: Text Arena Debut?
- 1480+-2.5pt66%
- 1490+-9.0pt51%
- 1500+-3.0pt23%
+2 mais resultados
- Largest IPO by market cap in 2026?
- OpenAI IPO Closing Market Cap
- When will Anthropic officially announce an IPO?
- Anthropic IPO Closing Market Cap
- When will OpenAI achieve AGI?
- Will Anthropic’s valuation hit __ by December 31?
- Will OpenAI's valuation hit __ by December 31?
- Next Google Gemini Pro Model released by which date?
- Best Chinese AI Company end of September?
- What will OpenAI's IPO valuation be?
Perguntas frequentes
- Quais são as probabilidades atuais de Will tailcalled think that the Shard Theory alignment research program has achieved something important by October 20th, 2026??
- A Manifold Markets cota No em 88% em 8 de setembro de 2026.
- Quando Will tailcalled think that the Shard Theory alignment research program has achieved something important by October 20th, 2026? é resolvido?
- Will tailcalled think that the Shard Theory alignment research program has achieved something important by October 20th, 2026? deverá ser resolvido em 20 de outubro de 2026.
- Como Will tailcalled think that the Shard Theory alignment research program has achieved something important by October 20th, 2026? é liquidado?
- A Manifold Markets liquida este mercado da seguinte forma: The Shard Theory research program by Team Shard is based on the idea that we should directly study the what types of cognition/circuitry are encouraged by reinforcement learning, and reason mechanistically about how reward leads to them, rather than the classic Outer Alignment/Inner Alignment factorization which aims to create a reward function that matches human values and somehow give an AI a goal of maximizing that reward.