Why do two experts with identical knowledge produce different outcomes in the same situation?
This explores why expertise can't be reduced to knowledge stock — two people who know identical things still act differently because expertise is judgment, performance, and communication, not just retrieval.
This explores why two experts with the same knowledge diverge in practice — and the corpus has a sharp answer: knowledge is the smallest part of expertise. The bigger part is *situational judgment* — knowing when to speak, when to defer, which piece of knowledge applies right now, and how to deliver it to this particular audience Is expertise really just knowing more than others?. Two people can hold the same facts and still read the same moment differently, because reading the moment is its own skill.
Part of that skill is *selecting which differences matter.* Expert observation isn't pattern-matching across everything in view; it's a qualitative choice about which details are relevant to this situation and this audience's needs Can AI distinguish which differences actually matter?. Give two experts the same scene and they may foreground different signals — and that single upstream choice cascades into different actions downstream. The knowledge is identical; the judgment about what's salient is not.
The other half is that expert claims are *communicative acts that anticipate a response.* A claim succeeds when it's both factually right and socially acceptable to the community hearing it, and experts are constantly running that second calculation — what will land, what will be accepted, what their standing lets them assert Can AI anticipate whether expert claims will be socially valid? Can AI replicate the communicative work experts do?. The same true statement carries different force depending on who says it and the track record behind it Can language models distinguish expert arguments from common assumptions?. So two experts with equal knowledge but different reputations, framings, or audiences will produce genuinely different outcomes — the difference lives in the social situation, not the facts.
There's a deeper reason the divergence is unavoidable: even the words don't mean the same thing to both. Referential grounding is person-specific — how language connects to the world has to be actively negotiated, not assumed from shared vocabulary Why do speakers need to actively calibrate shared reference?. The same explanation is effective or useless depending on the source-framing-recipient triad it lands in, not on anything intrinsic to the explanation itself What if XAI is fundamentally a communication problem?. The thing worth taking away: 'identical knowledge' is a fiction once you realize that expertise is a performance calibrated to a moment and an audience — which is also precisely the layer the corpus argues AI can't reproduce, because it has the text but not the standing, the situation, or the read of the room.
Sources 7 notes
Real expertise involves situational judgment—knowing when to speak, when to defer, which knowledge applies now, and how to communicate it to a specific audience. This role-performance dimension is at least as important as the underlying knowledge stock, and it is what AI cannot structurally perform.
Experts observe by choosing which differences matter (qualitative judgment); AI finds patterns and probabilities (quantitative). AI generates text from prompts without observing context, audience needs, or knowledge states—producing fabrication that mimics observation's form without its epistemic process.
Expert claims are validity claims that succeed when both factually correct and socially acceptable within a community. AI can estimate statistical correctness but cannot anticipate contextual acceptability because it lacks embedded knowledge of expert communities' evolving standards.
Expertise requires anticipating audience acceptability and social validity, not just retrieving information. AI lacks the mechanism to perform this communicative work, making its fluent output epistemically misleading despite its confident form.
LLMs lose the social context that gives expert claims their force—reputation, track record, and standing—because they process only text, not the social world where expertise is built and evaluated.
The same words can mean different things to different speakers because referential grounding is person-specific. True communicative grounding demands collaborative negotiation of how language connects to the world, not mere surface-level word sharing.
Explanation quality is not intrinsic to the explanation itself but depends on the rhetorical situation: who presents it, how it is framed, and what role the recipient plays. Evaluations that ignore this triad measure only a narrow slice of real-world effectiveness.