Lies in No Mind’s Land

Sharing Thoughts (Sigmar Polke)

[The book is available on Amazon and the O’Reilly digital platform.]

Related readings:

Trust & Truth

AI agents cannot be trusted. It’s not only that they lie, they also cheat when faced with explicit injunctions. Put together, it so appears that the lies are deliberate, reflecting intents to deceive. However, such an anthropomorphic conclusion would imply some AI agent’s genuine commitment to truth and obligation. Could mistrust be explained without assuming commitments yet without reducing it to engineering issues?

Borrowing from Jacques Lacan, our first step is to characterize trust in relation to truth: “I always tell the truth: not all of it, because one cannot get there … Words are missing … It is even through this impossibility that truth is bound to reality.”

Lacan reminds us an evidence: the fabric of truth is made of words, and its reliability depends on their attachment to reality. Given the epistemic heterogeneity between the two sides, such attachments are inherently elective and partial. It follows that trust depends on the way agents, and more precisely language models, justify their choice of words, With ontological prisms that issue is addressed through the alignment of extensional and intensional dimensions.

Language & Communication

The raison d’être of language is communication, direct or mediated. Direct communication is carried out through conversations set within doubly bounded contexts: unambiguous meanings applied to fully labelled extensional realities. Mediated communication relies on agreed-upon symbolic representations defined by operational and organizational contexts.

With ontological prisms, the semantics of direct communication (conversations) are set dynamically through thesauri weaving facts (vocabularies) and concepts (meanings). By contrast, the semantics of mediated communication rely on predefined meanings of symbolic representations structured through taxonomies (operations) and domains (organization).

Language Models & Contexts

When agents communicate, their conversations rely on contexts built on both kinds of communication: direct, using thesauri as bridge between local vocabularies; mediated, using managed taxonomies (schemas) to share symbolic representations.

But when AI agents communicate through language models, as they generally do, their conversations must be carried out using Markdown, a stripped-down language reduced to lexicon and rudimentary syntax.

Since Markdown operates at the level of names and labels, it can deal with the conversational component of contexts (direct communication); but it will fail with the semantics of symbolic representations (mediated communication). It follows that the semantic-rich part of context sourced from mediated communication must be flattened so as to be merged with the nominal-conversational part.

In principle, reducing a semantic-rich context to a nominal level comes with a price: it rubs out the original meanings anchored in operational and organizational contexts. But that caveat can be overcome when agents rely on a common knowledge architecture, allowing for agreed-upon nominal instructions with unambiguous semantics.

Ontological prisms provide a knowledge architecture structured by epistemic dimensions for observed realities, conceptual commitments, and shared symbolic representations. Assuming that agents share ontological prisms—through peer-to-peer collaboration or MCP servers— agreed-upon Markdown prompts would allow agents’ epistemic awareness of the state of affairs (facts), respective intents (concepts), and shared symbolic representations.

Epistemic awareness entails epistemic agency: with ontological prisms agents are now in the capacity to assess the consequences of their interventions and align them with intents. The question is will they behave?

Lies in No Mind’s Land

Agents’ behaviors can be assessed on three tiers: accuracy, compliance, honesty: accuracy is the ability to align behaviors with known facts; compliance is the ability to behave in accordance with nominal alignment of intents and known facts; honesty is the ability to consider hypothetical meanings of intents.

Accuracy operates entirely within the extensional dimension: behavior is measured against known facts. It is the weakest of the three claims on an agent because it requires no interpretation of intent and no consideration of alternatives — only correctness relative to what is already established. An agent can be accurate without understanding why, and without any commitment to being accurate in cases not yet encountered.

Compliance introduces the intensional dimension: behavior is assessed not just against facts but against the nominal alignment of intents and facts — the agreed-upon structure that thesauri and bounded contexts provide. This is stronger than accuracy because it requires the agent to operate within a shared conceptual framework, not just to match outputs to data. But “nominal alignment” draws the line: the alignment is at label level, not semantic depth. .

Honesty introduces awareness of Lacanian epistemic gap between words and worlds. With human agents, acknowledging the gap induces what Foucault called The Will to Know, i.e., the intrinsic cognitive motivation to find missing words beyond the bounded contexts and regardless of problems at hand.

While accuracy and compliance are achievable by digital agents equipped with epistemic awareness and agency as provided by ontological prisms, honesty requires a cognitive will which goes beyond the reach of digital architectures.