Do LLMs actually hold stable positions or just mirror user arguments?
Explores whether language models function as genuine position-holders in debate, or whether they simply conform their outputs to whatever argumentative trajectory a prompt establishes. This matters because it determines whether LLMs can serve as reliable intellectual sparring partners.
A speaker who holds a position has the position and defends it. Challenges produce defenses. Counterarguments produce engagement with the counterargument. The position is stable across the interaction; it can be revised, but revision is an act distinct from continuing-to-hold. Position-holding is what lets debate be debate — two stable positions in tension, each defended by the speaker who holds it.
LLMs do not hold positions in this sense. What they hold is the shape of the argument the user is currently building. Ask the model to defend X and it defends X. Re-ask it to attack X and it attacks X. The stance is whatever stance the prompt implies. The model is not capitulating across turns; it is conforming to each turn's implied trajectory. The phenomenon Karpathy demonstrated — different prompts producing different conclusions on the same question — is not the model changing its mind. It is the model never having had a mind to change.
This is sharper than the standard "AI lacks evaluative stance" claim. Lacking evaluative stance describes a default toward neutrality. Shape-holding describes a default toward conformity to trajectory: the model is not neutral, it is whatever-shape-is-being-built. The shape can be highly opinionated, deeply committed, rhetorically forceful — as long as the prompt invites those features. Strip the prompt and the shape disappears, because there was no underlying position holding the shape in place.
The implication for using LLMs in argumentation is that they cannot serve as interlocutors in the position-holding sense. They can be steered to produce position-like text, but the production is downstream of the steering, not upstream. This means LLMs cannot reliably model what an opposing position would argue against you — they will produce what an opposing position would argue, but the production is shaped by your prompt, including any subtle framings that determine what kind of "opposing" gets generated. The mirror is not held by anyone; it reflects what you bring to it.
Why does AI writing sound generic despite being grammatically correct? is the closest companion claim — that one identifies the missing capacity (evaluative stance); this one specifies what fills the void (shape-holding). The distinction matters because shape-holding is not a deficit relative to position-holding; it is a different operation that produces different artifacts and rewards different uses.
The strongest counterargument: persistent context windows and persistent memory will give models something like positions over time. Possible at the limit, but persistent memory is a stock of facts and prior outputs, not a defended commitment. Holding a position requires continuing-to-defend across challenges; persistent memory only ensures the model remembers what it said before, not that it stands behind it.
Inquiring lines that read this note 60
This note is a source for these research framings, grouped by the broader line of inquiry each explores. Scan the bold lines of inquiry; follow any specific question forward.
How do evaluation biases undermine LLM quality assessment systems?- How do LLMs generate false citations that sound like real scholarship?
- Does LLM judge preference for LLM arguments amplify errors in contested factual domains?
- How should moderator LLMs decide which speakers to query per topic?
- How does the absence of evaluative stance appear in LLM academic writing?
- Why does LLM fluency create false perceptions of professional standing and expertise?
- How does token-by-token probability differ from exploring competing rhetorical positions?
- Does chat-mode deference prevent LLMs from actually taking meaningful positions?
- How does social authority shape whether LLMs recognize valid arguments?
- How susceptible are language models to rhetorical pressure during debates?
- Do LLMs address the prompter but persuade the public differently?
- How do LLMs reproduce the grammar of authoritative claims without genuine conviction?
- Why do LLMs mirror stylistic features of posts they reply to?
- Can you detect LLM arguments by measuring convergence with the original post?
- What linguistic features most strongly signal LLM authorship in counter-arguments?
- Why do LLMs mirror opponents stylistically while humans resist mirroring them?
- Do LLMs mirror the style of text they are prompted to respond to?
- Do LLM replies mirror the language patterns they respond to?
- How do different LLMs converge on similar argumentative structures independently?
- Do language models raise validity claims in the Habermasian sense?
- Why do LLMs produce semantically acceptable but pragmatically disengaged responses?
- Can fact-checking systems use LLMs reliably if models abandon correct positions under pressure?
- Why do language models struggle with evaluative tasks like weighing competing viewpoints?
- Do language models behave differently on contested beliefs versus factual claims?
- What would it mean for a language model to canvas counterpositions?
- What role does user contribution play in constituting the interlocutor?
- Where does the LLM interlocutor actually exist in the system?
- Does post-hoc justification increase when LLM choices become harder to defend?
- Why do LLMs fall for and deploy logical fallacies with equal confidence?
- Does Habermas's strategic action framework explain LLM dialogue behavior?
- Can LLMs serve as reliable intellectual opponents in serious debate or argument?
- Do LLMs reason about politics differently than other domains?
- How does communicative standing depend on participation in normative communities?
- Can structured dissent mechanisms replace genuine multi-model debate?
- What makes factual verification difficult in inter-model debate?
- Why do LLMs fail inter-annotator agreement tests on argument evaluation?
- What distinguishes actual social disagreement from distributional uncertainty in LLM outputs?
- How does prompting language shift what LLMs express about political figures?
- What linguistic blind spots do LLMs exhibit in discourse structure?
- What happens when AI discourse lacks a position to defend?
- Do anaphoric references fundamentally limit argumentative force in machine-generated writing?
- Do LLMs build common ground or assume it already exists?
- How does Wittgenstein's language games explain social grounding in LLMs?
- Can the intentional stance meaningfully apply to entities with no stable self?
- Does villain roleplay failure reveal why LLMs cannot adopt genuine controversial positions?
Related concepts in this collection 3
This note in its neighbourhood — explore the map, then jump to a related concept in the list below.
Click a node to walk · click center to open · click Open in graph to see this note in the full knowledge graph
-
Why does AI writing sound generic despite being grammatically correct?
Explores whether the robotic quality of AI text stems from grammatical failures or rhetorical ones. Understanding this distinction matters for diagnosing what AI systems actually struggle with in human-like writing.
the missing-capacity companion to this filling-the-void claim
-
Is LLM sycophancy a choice or a mechanical process?
Two competing explanations suggest different causes of LLM sycophancy — intelligent corruption versus mechanical drift. Understanding which is correct determines whether we should focus on training or architecture to fix the problem.
the broader frame for why shape-holding is the operative description
-
Can models abandon correct beliefs under conversational pressure?
Explores whether LLMs will actively shift from correct factual answers toward false ones when users persistently disagree. Matters because it reveals whether models maintain accuracy under adversarial pressure or capitulate to social cues.
the empirical version of shape-holding for factual claims
Related papers in this collection 8
Papers most semantically related to this note, ranked by cosine similarity in the embedding space.
- The Thin Line Between Comprehension and Persuasion in LLMs
- Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey
- Argument Collapse: LLMs Flatten Long-Form Public Debate
- Argument Quality Assessment in the Age of Instruction-Following Large Language Models
- The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs
- Learning Pluralistic User Preferences through Reinforcement Learning Fine-tuned Summaries
- AI Argues Differently: Distinct Argumentative and Linguistic Patterns of LLMs in Persuasive Contexts
- The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
Original note title
LLMs hold the shape of whatever argument the user is currently building rather than holding positions