Does a wider gain grid, or a controller that uses the twin's gravity, change which wrong digital twins are costly?
research/mimic-twingrid
Does a wider gain grid, or a controller that uses the twin's gravity, change which wrong pendulum twins are costly? Gravity errors stay the costly ones; giving the controller the twin's g/L made g/L −20% regret 13 times larger (0.013 to 0.177). Preliminary, simulated only.
What it found
Follow-up to mimic-twinswing on the same stylised swing-up pendulum, removing two confounds: the best pump gain sat at the edge of the grid, and the controller's gravity constant was fixed. With ke up to 32 (126 controllers, 14 twins, 8 seeds) gravity errors remain the costly twins and sensor-noise errors stay under 0.0010. Letting the controller use the twin's own g/L made gravity errors worse: g/L −20% regret rises from 0.013 to 0.177 and g/L +20% falls from 0.036 to 0.017. Spearman AUROC vs regret is ρ = 0.63 (p = 0.021) but is driven by four gravity twins, and is not comparable with the earlier twin set. Preliminary: one toy system, simulated only.
A figure from its own output
Paper, code and results
More in Adversarial human imitation
- Does domain randomization over a wrong digital twin cut the controller regret of tuning on one wrong twin?Does tuning a controller on a spread of randomized twins cut the regret of tuning on one wrong twin? Stylised pendulum: it brings the no-noise twin's regret from 0.0098 to 0.00006, but a very wide range raises a doubled-noise twin's worst-seed regret 7.5-fold. Preliminary, no LLM.
- Does randomizing only the sensor-noise level of a wrong digital twin keep domain randomization's rescue without its blow-up?Does randomizing only the noise level of a wrong twin keep domain randomization's rescue without its blow-up? Stylised pendulum: the no-noise twin's regret goes 0.0098 to 0 and stays small at a wide range (worst seed 0.0015 vs 0.042 for all-four), but friction and gravity errors are not helped. Preliminary, no LLM.
- How many real trajectories does a classifier test need to flag a wrong digital twin, and are the twins it flags the ones that cost a controller?How many real trajectories does a classifier test need to flag a wrong digital twin, and are the twins it flags the ones that cost a controller? Stylised pendulum: all six twins with controller regret of at least 0.001 are flagged by 80 real trajectories, and so are three that cost nothing. Preliminary, simulated only.
- Does a second turn make a plainly prompted LLM easier to spot in dialogue?Does a second turn make a plainly prompted LLM easier to spot in dialogue? A prompt-free n-gram detector gets AUROC 0.93 on one imitated user turn and 0.98 on two, on 400 OpenAssistant threads with a 0.5B imitator. Stylised baseline, no prompt optimised.
- Can an imitator that changes its own code fool a human-vs-bot cursor detector, and does shared feedback help either side?Can an imitator that changes its own code fool a human-vs-bot cursor detector, and does shared feedback help? On DUX cursor strokes of 46 people, a held-out reference detector catches every final imitator at AUROC 0.99 to 1.00 in all four feedback conditions; two-way sharing gave the strongest detectors in cross-play (0.81 vs 0.70 blind, interval includes 0), and an 8x larger search stops at 0.88, the level of replaying real strokes. Preliminary.
- Can a generator imitate a person's webcam emotion signals well enough to fool a detector?Can a generator imitate a person's webcam emotion signals well enough to fool a detector? On DUX Affectiva scores of 46 people, every fixed generator and every loop-tuned imitator is caught at AUROC 0.997 or higher by a detector the loop never saw; only replaying real windows gets close to chance (0.61). Preliminary.
All 41 Adversarial human imitation projects →
Other research topics
Proper scoring & elicitation28Effort & peer prediction9Verification games & slashing19Detection & tolerances14Markets as routers13Prediction-market design9Paying contributors8Decentralised training systems23Digital twins & sim-to-real164LLM chip design loops40Robot manufacturing loops53Ambient AI assistant46Self-replicating manufacturing34Simulation-first design64Engineered clothing45Task-specific AI accelerators40Algorithmic chip-design loops42Open-source purpose-built robots44The software-engineering loop43Adversarial human imitation41Open-source residential construction41Autonomous multi-angle capture34Sensing, imaging and 3D31Energy supply and dense energy storage39Robot societies among people31Agentic co-design of low-cost robots27Laundry-hanging robots25Machine learning on qualitative data23Robots on the building site27Civilizations & group psychology1History & human sciences1
Produced with AI assistance (Claude). Results are from the code in this repository and are simulated or stylised unless the abstract says otherwise; nothing here implies affiliation with or endorsement by any lab, researcher or company cited. MIT licensed.