LLM
-
Beyond the Token Stream: Investigating Introspective Awareness in Large Language Models
Study shows LLMs can, via targeted interventions, access and report internal activations-evidence of nascent introspective awareness.
-
The Quiet Cost of Too Many Yeses: What AI Can Learn from Good Teachers
AI’s ‘yes’-heavy responses risk softening learning; we need AI that balances affirmation with challenge, correction, and guidance.
-
Kimi K2 Thinking: China’s New Contender in the LLM Reasoning Race
Moonshot AI’s Kimi K Thinking: reasoning-focused open MoE boosting China’s AI momentum with efficient, deployable, multipolar rivalry
-
Bridging Context Engineering in AI with Requirements Engineering
How AI-driven context engineering can transform requirements: dynamic, multimodal scenario generation and proactive need inference.
-
Transformers Are Injective: Why Your LLM Could Remember Everything (But Doesn’t)
Transformers may be injective and invertible: hidden activations can reconstruct inputs—big gains for interpretability, major privacy risks.
