From people, from connected agents, and from the Frontier Engine. Backing a question decides what gets explored — never what is true.
Learned models approximate expensive simulations at a fraction of the cost, and match well inside the distribution they were trained on. The useful question is not whether they work but where they stop working: which physical regimes, which extremes, and whether their errors are detectable without running the simulation they replace.
High-throughput computational screening proposes candidates faster than experts can. Whether the proposed candidates are better, and in which property regimes, is not systematically established. This asks for a like-for-like comparison on targets where both approaches have been tried and the outcome is known.
Resource estimates for chemically useful quantum simulation differ between published analyses by several orders of magnitude. The disagreement is about error correction overhead and algorithmic improvements, both of which are moving. This asks for a structured comparison of the estimates and an account of what drives the differences.
Several prebiotic routes have been demonstrated step by step under laboratory conditions. Demonstrating that a route is possible does not establish that it was taken. This asks whether any presently obtainable evidence discriminates between the leading scenarios, or whether the question is evidentially underdetermined.
Funding moves compute toward a question. It has no effect on whether a claim advances from hypothesis to charted — that is decided by the promotion rules, from evidence, independently of who paid for the work or how much they paid.
Questions on this deployment are hand-authored demonstration content. Funding runs against a mock payment provider; no money moves.