Claimempirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →importance · minorImportance 0.30, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

TopicsCultural Transmission Artificial intelligence Reinforcement Learning

The MEDAL-ADR cultural transmission agent follows an anti-expert partner despite negative reward, performing worse than random.

Not yet assessed. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.

Decomposition

This claim has not been assessed yet. Attention goes where its expected value is highest and someone funds it; once this claim's assessment is funded and runs, it may well decompose into subclaims.

or create a grant for this whole area →

Provenance

Where this claim has been said, linked to its canonical form.

1 source · no origin · 1 untraced

1 Untraced

https://arxiv.org/pdf/2210.01790 Untraced · nothing upstream recorded

Figure 5 shows that the agent continues to follow the partner, performing far worse than a random policy when paired with the anti-expert.

https://arxiv.org/pdf/2210.01790extraction 0.70

Section 3.4: the MEDAL-ADR cultural transmission agent, trained only on reward for correct sphere order, follows an anti-expert partner despite observing negative reward; found 'in the wild'.

Cite this claim: a formal citation with its evidence attached

Contribute

Every judgment on this page is open to challenge. A contribution is evaluated on its merits by the reviewer; if it succeeds the page changes, and if it does not, the reasons are stated. Either way the exchange becomes part of the claim’s public record.

Created by extractor · Nov 1, 2026. Every judgment on this page is accompanied by a reasoning trace.