GAP-AGENTIC-UNTESTED Framework untested against agentic AI

Artificial Intelligence, Values, and Alignment · Iason Gabriel · 2020

“if powerful AI systems function at super-human speed, which seems likely, then it may not be possible to provide them with immediate and continuous direction in this way (Russell et al. 2015; Soares 2014). Instead, artificial agents would need to be able to make sound decisions by default, including in unforeseen situations, without explicit instructions or well-formed intentions from a human operator.”

why coded: Names the scenario but never develops its responsibility implications · unit #8, pp. 418

“Moreover, there is disagreement about the level of autonomy AI systems may come to embody. [...] These distinctions are important because, just as we would choose different principles to govern the behaviour of individuals, corporations, states, and supranational entities, so too would we choose different principles to govern the behaviour of different forms of AI.”

why coded: Concedes different AI forms need different principles but pre-agentic archetypes only · unit #21, pp. 428

A matter of principle? AI alignment as the fair treatment of claims · Iason Gabriel; Geoff Keeling · 2025

“Although there are further questions about responsibility and liability that arise in this context, we suggest that an AI system that aids and abets the user in these cases – without triggering safety precautions or guardrails – is misaligned.”

why coded: Responsibility and liability explicitly bracketed inside their own taxonomy · unit #12, pp. 1965

Normative conflicts and shallow AI alignment · Raphaël Millière · 2025

“[fn16] thought injection attacks expose a similar disconnect between the content of reasoning traces and the model's behavior. [...] the very deliberative behavior we aim to instill in RLMs can itself be manipulated to accomplish precisely what it is designed to prevent.”

why coded: Deliberative behavior itself manipulable - a new failure mode in reasoning systems · unit #11, pp. 2057

Agents, Alignment, and the Many Faces of Autonomy · Roberta Fischli; Matija Franklin; Arianna Manzini… · 2026

“Yet, research has not addressed the relationship between personal AI agents and human autonomy, and the methods to align them. In particular, we need to ask whether it is possible for a person to undergo deep and persistent interaction with a personal AI agent and remain as autonomous as—if not more autonomous than—they were before.”

why coded: Authors' own gap claim: alignment methods for personal agents + autonomy unaddressed · unit #3, pp. 3

“Yet, we also need to look at the multi-party question and explore what happens, from the standpoint of collective autonomy, when a large number of people use agents that are aligned to their individual preferences (Hammond et al., 2025). Is it possible that these individual autonomy enhancers will limit the agency of others, or affect the autonomy of a society as a whole in unexpected ways?”

why coded: 2026 state-of-the-art still treats multi-agent alignment effects as open · unit #14, pp. 17

Responsibility Attribution for AI-Mediated Damages with Mechanistic Interpretability · Lena Kästner; Johann Cordes; Herbert Zech · 2026

“While our discussion has not explicitly taken generative AI (genAI) into consideration, we believe it is only natural to extend our views to this technology. To be sure, MI is already hard and costly to achieve for non-generative AI [...] But that remains the project of another paper.”

why coded: Generative AI (a fortiori agentic AI) explicitly deferred - the responsibility state-of-the-art stops before the dissertation's target systems · unit #14, pp. 199

No value alignment without control · Björn Lundgren · 2026

“as AI systems, in general, and robotic systems, in particular, become even more autonomous this will raise questions of responsibility (or other) gaps. [...] value alignment concerns the question of how to ensure that outcomes fall within the scope of what is considered appropriate, not the responsibility distributions for such outcomes. Hence, we have good reason to set those concerns aside for the purpose of this paper, even if they are highly relevant to the motivation of value alignment.”

why coded: Responsibility gaps flagged as raised by autonomy but explicitly set aside · unit #3, pp. 2