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 (335B)


      1 {
      2   "paper_type": "empirical",
      3   "reason": "The paper runs comparative experiments evaluating LLM baselines against SAE-based methods for model diffing, reporting quantitative results on accuracy, frequency, and interestingness metrics; the primary contribution is the experimental finding that simple LLM baselines are competitive."
      4 }

Impressum · Datenschutz