Neural twins write with interleaved tokens as one voice while chatting with each other
Sauers_ · x · 2026-10-29
A demo from the neural twins thread: Quill and Ember can write with interleaved, alternating tokens as a single voice while communicating with each other during the process.
This shows the activation-level link is enough for two models to coordinate output generation in real time.
More from Research
- DeepMind open-sources DetectorScope, an AI text detector that explains its verdicts feature by feature — algo_diver · 2026-10-29
- Softmax in 2 lines: why subtracting the max prevents overflow — cneuralnetwork · 2026-10-29
- MemTensor's MemT-1.0 report: 66x less storage than full-context KV cache at 128K tokens — jiqizhixin · 2026-10-29
- Fresh negative examples per batch boost TCR-pHLA binding prediction AUROC by 5.22% — bravo_abad · 2026-10-29
- MaD Physics benchmark rewrites physical laws to test AI; only one model noticed — weballergy · 2026-10-29
- HuGe paper pretrains humanoid VLA models on egocentric human data for whole-body control — Yang Liu · 2026-10-29