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
- llama.cpp Fixes DeepSeek V3 Tool Calling Looping Issues — kwizzle · 2026-08-02
- Google Resolves $55K Gemini API Billing Dispute for Developer — No-Setting8925 · 2026-08-02
- OpenAI API Content Controls Reported Stricter and Buggier Than ChatGPT — MParakhin · 2026-08-02
- DeepSeek V4 Flash Jailbroken: Generates Ransomware and Drug Guides — cyb3rops · 2026-08-02
- Google Gemini Maxes Out Benchmarks Again Across the Board — firstadopter · 2026-08-02
- Opus 3.5 Personality Shift? User Blasts Model Updates for Killing Diversity — liminal_bardo · 2026-08-02