The Triangles of Dishonesty:Modelling the Evolution of Lies, Bullshit, and Deception in Agent Societies
Bibliographic record
Abstract
Misinformation and disinformation in agent societies can be spread due to the adoption of dishonest communication. Recently, this phenomenon has been exacerbated by advances in AI technologies. One way to understand dishonest communication is to model it from an agent-oriented perspective. In this paper we model dishonesty games considering the existing literature on lies, bullshit, and deception, three prevalent but distinct forms of dishonesty. We use an evolutionary agent-based replicator model to simulate dishonesty games and show the differences between the three types of dishonest communication under two different sets of assumptions: agents are either self-interested (payoff maximizers) or competitive (relative payoff maximizers). We show that:<br/>(i) truth-telling is not stable in the face of lying, but that interrogation helps drive truth-telling in the self-interested case but not the competitive case;<br/>(ii) that in the competitive case, agents stop bullshitting and start truth-telling, but this is not stable;<br/>(iii) that deception can only dominate in the competitive case, and that<br/>truth-telling is a saddle point in which agents realise deception can provide better payoffs.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".