20.500.12556/RUP-22641 Predictable artificial intelligence Many areas of artificial intelligence, and machine learning in particular, aim at being probably correct, i.e., valid on average, rather than pursuing the idealistic goal of being provably valid for all inputs. However, AI systems could still be predictably valid, such as an imperfect robot deliverer for which we can reliably and precisely predict the task instances for which it is correct and safe, its valid operating range. “Predictable AI” is a nascent research area that explores ways of anticipating key validity indicators (e.g., performance, safety) of present and future AI ecosystems. We argue that achieving predictability is crucial for fostering trust, liability, control, alignment and safety of AI, and thus should be prioritised over performance. We formally characterise predictability, explore its most relevant components, illustrate what can be predicted, describe alternative candidates for predictors, as well as the trade-offs between maximising validity and predictability. To illustrate these concepts, we bring an array of illustrative examples covering diverse ecosystem configurations. “Predictable AI” is related to other areas of technical and non-technical AI research, but have distinctive questions, hypotheses, techniques and challenges. This paper aims to elucidate them, calls for identifying paths towards a landscape of predictably valid AI systems and outlines the potential impact of this emergent field. predictable AI general-purpose AI AI safety napovedljiva UI generalno inteligentna UI varnost UI true false true Angleški jezik Slovenski jezik Članek v reviji 2026-02-09 08:04:26 2026-02-09 08:04:30 2026-02-10 03:06:56 0000-00-00 00:00:00 2026 0 0 str. 1-21 article 104491 Vol. 353 Apr. 2026 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 2026-01-30 004.8 1872-7921 10.1016/j.artint.2026.104491 267372803 RAZ_Zhou_Lexin_2026.pdf RAZ_Zhou_Lexin_2026.pdf 1 01E78DFB20707B7A4BA7EEAAFDDF1502 5b1826cf32ab386c8b559f7f0820343078e2199f566712228a5fb3edb5511c8e dd955a3c-0585-11f1-b092-005056ac49c0 https://repozitorij.upr.si/Dokument.php?lang=slv&id=32945 https://www.sciencedirect.com/science/article/pii/S0004370226000172 1 9b7f76aa-0585-11f1-b092-005056ac49c0 https://repozitorij.upr.si/Dokument.php?lang=slv&id=32944 Fakulteta za matematiko, naravoslovje in informacijske tehnologije 0 0 0