paper_type.json (211B)
1 { 2 "paper_type": "empirical", 3 "reason": "Proposes confessions trained via RL and reports quantitative experimental results (confession rates, detection accuracy) on GPT-5-Thinking across 11/12 evaluations." 4 }
ai-research-surveySystematic scan of agentic development research. What's signal, what's noise. | |
| git clone https://git.shiptheloop.com/ai-research-survey.git | |
| Log | Files | Refs |