Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
We haven't written up this one. ByteByteGo has the full story — the link below goes straight to it.
More in AI
FLock.io Says Qwen-Based Decision Model Outperforms Larger LLMs on Selected Tasks
London-based FLock.io announced on October 13 that it has introduced THIS / THAT Model, a small, open-source AI model designed for fast, low-cost decision-making rather than open-ended text…
- FLock.io launches THIS/ THAT Model on October 13
- Model outperforms larger LLMs like GPT-5.6 and Claude Opus 5
- THIS/ THAT Model processes 2.5 million decisions in three weeks
AI Robots Help Railway Maintenance During Labor Shortages
Seibu Railway demonstrated a trial of autonomous robots equipped with physical artificial intelligence (AI) at an electrical substation in Tokyo on October 14, testing technology designed to…
Readily secures $11M series A to continue building out AI regulatory compliance platform
Artificial intelligence compliance platform Readily raised $11 million in series A funding to support development of its enterprise oversight platform.
AI agents make 138 million crypto payments as U.S. dominates spending on AI models
U.S.-linked wallets account for just over 88% of tracked AI model payments, dwarfing China’s 0.1% share, according to new Chainalysis research.