Qiezli – a ‘Self-Absorbed’ creative virtual agent in Second Life
Bibliographic record
Abstract
This article describes the implementation and artistic evaluation of an abstract, believable virtual agent known as Qiezli. Possessing the ability to create aesthetic output by itself, Qiezli functions as an automated performance artist in Second Life (SL). Seemingly pre-occupied with its own daydreaming imagination, Qiezli is visually inspired by Josephine Anstey’s narrative-embedded zoomorphic agent, ‘The thing growing’ (2000). Qiezli uses aesthetic abstraction, Non-Verbal Communication (NVC) and combinatorial creativity to interact with SL-avatar participants beyond the confines of a goal-oriented narrative. This research catalyses methods for simulating alien ontologies and stereotypically western (i.e. Enlightenment and Romantic-era) artistic behaviours in user-generated virtual worlds. Qiezli appears alien not only via its abstract appearance but also through its idiosyncratic usage of expressing itself non-verbally by wearing video-textures in response to avatar interactions. Whereas character-traits such as self-absorption or aloofness are not usually seen as a benefit to interactivity; Qiezli’s insistence on focusing on its solitary daydreaming state mirrors a stereotypical characteristic among Romantic artists who chose to transcend society by detaching from it. This article contributes to the metaverse art-discourse by showing the perceptual and technical limitations of designing an agent in SL – especially one that is meant to be visually and behaviourally distinct from a human-controlled avatar. The main limitations are due to SL’s proprietary Linden Scripting Language (LSL) and its design that structures agent behaviour around a finite-state architecture comprised of event-activated gestural loops. Based on the observation results from representatives from SL’s artistic community; the authors now suggest that Qiezli or an equivalent agent be produced using a more robust cognitive architecture. Therefore, Qiezli would appear less reactive by managing external memory-storage and engage in genuine deliberation of states and operators.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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) | 0.045 | 0.005 |
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; both teacher heads agree on what is shown here.
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".