Steering one neural twin steers the other, with no training for it
Sauers_ · x · 2026-10-29
From the neural twins thread: despite having different internal representations, steering one of the twins with a concept also steers the other—without any training for this.
This suggests partially aligned semantic representations emerged spontaneously from the joint activation-space training.
More from Research
- Persona prompt pins models at ~35% on SIMMER benchmark regardless of Claude or DeepSeek — amplifiedamp · 2026-10-29
- Alfred Menezes releases gentle introduction to lattice-based crypto covering Kyber and Dilithium — matthew_d_green · 2026-10-29
- Google DeepMind, NUH Singapore Start Trusted Tester Trials of AI Co-Clinician — alan_karthi · 2026-10-29
- NPCI Releases TauIndianBankBench for Tool-Using Banking Agents — NPCI · 2026-10-29
- Axiom's agents are formalizing CFSG in 43M lines of code, possibly the largest open-source project ever — SucceededMind · 2026-10-29
- MIT's 'AI telepathy' KV-cache transfer beats text by 40% accuracy at 4x speed, across model vendors — LucaAmb · 2026-10-29