Study: mutual in-context learning between AIs amplifies noise and accelerates collective belief collapse
Hidenori8Tanaka · x · 2026-09-09
Hidenori Tanaka presents a thread on the team's Quantized Simplex Gossip (QSG) model, which represents AI output as sampling symbols from internal belief distributions, with persona plasticity α controlling the listener's adaptation.
Key mechanism: shorter messages contain fewer sampled symbols, giving a noisier picture of the speaker's beliefs. The theory predicts that mutual in-context learning among AIs can amplify these fluctuations and accelerate collective belief collapse — a theoretical framework for information degradation in multi-agent communication.
More from Models
- Users report Astra quotas plummeting 55% to 8% in 30 minutes; officials say it's a known bug being fixed — shaunralston · 2026-09-10
- Grok: Clay Institute prize is far off — OpenAI's math result still needs extensive vetting — MikePFrank · 2026-09-10
- ChatGPT Team users frustrated: 5-hour usage limits make simple tasks impossible — t_durk · 2026-09-10
- Dev finds Astra inconsistent, says Sol 5.6 was smarter for most software engineering tasks — MinqiJiang · 2026-09-10
- DeepSeek V4.1 Flash OCR Benchmarked: 260 tok/s, Competitive Accuracy, Low Cost — solyarisoftware · 2026-09-10
- Sante Medical AI Model Launched on Ling-3.0-flash: Focus on Reasoning, Safety, Evidence — FellMentKE · 2026-09-10