Manifold MarketsSem KYCDados de resolução verificadosRazoavelmente calibradoPrevisão da comunidade atualSim 67.5%
Previsores
147
Tipo de pergunta
binary
Metodologia
Play-money forecasting platform
Tipo de fonte
Previsão
Dados do mercado
Atualizado há 11 minutos
30/09/26, 07:07 UTC25/10/26, 06:59 UTC
Tendências
Mercados Relacionados
Perguntas relacionadas para dar contexto, não uma comparação de contratos equivalentes.
In 2028, will LLMs still be able to get Gary Marcus to make egregious errors?
Manifold MarketsIn 2028, will Gary Marcus still be able to get LLMs to make egregious errors?
Manifold MarketsWhat will Claude Opus's output token price hit in 2026?
PolymarketNext Claude Opus (5.6+) released by which date?
PolymarketClaude Opus 5 METR 50% time horizon
Manifold MarketsClaude Opus 5 METR 50% time horizon [old version, bad buckets]
Manifold MarketsRegras
Third time's the charm?
- Scott Alexander has a market resolving in 2028 about whether Gary Marcus will be able to find "three extremely obvious questions, that an average human teenager could certainly answer, which a leading chatbot still fails at at least half the time when asked." (Weird adversarial hacks don't count.)
- A year and a half ago, I thought maybe ChatGPT o3 was smart enough that it was there already.
- A few months later, I thought GPT-5-Thinking might've gotten there.
- So now it's been more than another year and maybe Claude Opus 5.5 is there?
- To resolve YES, that it still makes egregious errors, we need, by market close [UPDATE: By the deadline listed below], just one example I can replicate [in a Temporary Chat] (no access to my chat history) with effort set to max.
