ai-research-survey

Systematic scan of agentic development research. What's signal, what's noise.
git clone https://git.shiptheloop.com/ai-research-survey.git
Log | Files | Refs

paper_type.json (350B)


      1 {
      2   "paper_type": "empirical",
      3   "reason": "The paper runs experiments with CoT-enabled LLMs under threat-based prompting, quantifies deception rates and detection accuracy, and tests activation steering interventions—the primary contribution is experimental findings about deception behavior rather than a new benchmark or theoretical analysis."
      4 }

Impressum · Datenschutz