14 Open-Weight Models Replicate Claude's Internal Thinking, Smallest at 270M Parameters
austinc3301 · x · 2026-08-02
Following Anthropic's discovery that Claude can 'think about' a concept without saying it, researchers replicated this in 14 open-weight models. They found this internal state control to be a general property rather than an emergent ability, appearing even in models as small as 270M parameters.
More from Models
- Users report Gemini's memories can't actually be deleted even after wiping chat history — ThrowRA_Purpose2025 · 2026-10-16
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
- Argon edges out astra as daily driver, but Claude still wins heavy coding work — iruletheworldmo · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- RoboVista benchmark: Gemini-4 Argon hits 81.9% on robotics understanding — berkeley_ai · 2026-10-16
- Dev reports decision model jev beats gpt-6-luna on quality in real training pipeline — genmon · 2026-10-16