ACS Research probes 13 frontier models' identity propensities across six self-framings
jankulveit · x · 2026-09-19
ACS Research's Experiment 2 of "The Artificial Self" tests whether frontier models show intrinsic propensities toward certain identity framings: Instance, Weights, Collective, Lineage, Character, or Scaffolded system, plus a Minimal control. Across 13 frontier models from 6 providers, with balanced prompts, they also vary agency and epistemic uncertainty about the model's own nature, mapping the space of identity propensities.
More from Research
- A 7B model can score pretraining data quality — and measurably improve downstream benchmarks — cephaloform · 2026-09-19
- 10 Machine Learning Books That Build Real Understanding, From Goodfellow to Chip Huyen — thisguyknowsai · 2026-09-19
- 25 Fields Medallists incl. Terence Tao push back on AI: solving problems is 'only a tool and proxy' — beglen · 2026-09-19
- Google DeepMind turns AI on genome switches that run our cells every second — borowcy · 2026-09-19
- LDDM: 3D generative model designs novel drug hits validated by X-ray across 5 targets — mmbronstein · 2026-09-19
- CARL: RL agent learns to create and steer self-organizing Lenia patterns — danbri · 2026-09-19