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 (306B)


      1 {
      2   "paper_type": "empirical",
      3   "reason": "Conducts experiments measuring vulnerability rates in LLM-generated code (9.8%-42.1%) and quantifies the effectiveness of different guidance strategies, with the primary contribution being empirical findings on code generation flaws and mitigation techniques."
      4 }

Impressum · Datenschutz