https://wiki.alt-text.eu/index.php?action=history&feed=atom&title=Emergent_capabilitiesEmergent capabilities - Revision history2026-09-15T06:23:50ZRevision history for this page on the wikiMediaWiki 1.45.3https://wiki.alt-text.eu/index.php?title=Emergent_capabilities&diff=36&oldid=previmported>ALT-TEXT: Import: AI terminology and people glossary2026-09-07T10:36:21Z<p>Import: AI terminology and people glossary</p>
<p><b>New page</b></p><div>== Emergent capabilities ==<br />
Abilities that appear in a large AI model without having been directly trained for, and that are not present, or are much weaker, in smaller versions of the same model, such as basic arithmetic or multi-step reasoning emerging once a [[Large language model (LLM)|large language model]] passes a certain scale. The phenomenon is well documented but poorly understood, and is one reason model behaviour can be difficult to predict in advance. (See also: [[Scaling laws]], [[Large language model (LLM)|Large language model]])<br />
<br />
[[Category:Glossary]]<br />
[[Category:Artificial Intelligence]]<br />
[[Category:Generative AI]]<br />
[[Category:AI Ethics]]<br />
</div>imported>ALT-TEXT