Topics
What the research is about
18 subjects in this area
- LLM Alignment 71 notes
- Argumentation and Persuasion 40 notes
- NLP and Linguistics 25 notes
- Discourse Analysis 22 notes
- Philosophy and Subjectivity 19 notes
- LLM Failure Modes 17 notes
- Natural Language Inference 16 notes
- LLM Evaluations and Benchmarks 15 notes
- Theory of Mind 12 notes
- Human-Centered Design 11 notes
- Social Theory and Society 9 notes
- Personas and Personality 9 notes
- Prompts and Prompting 5 notes
- Sentiment, Semantics, and Toxicity Detection 5 notes
- Role-Play and Persona Behavior 5 notes
- Design Frameworks 2 notes
- Social Media and AI 2 notes
- Decision Support Tools 1 note
6 subjects in this area
12 subjects in this area
- Multi-Agent Architectures 70 notes
- Agent Harness 39 notes
- Frontier AI Risk & RSI 30 notes
- Autonomous Agents 29 notes
- LLM Agents 16 notes
- Agentic Research and Workflows 14 notes
- Tool Use and Computer-Use Agents 10 notes
- Action Models 9 notes
- Visual and GUI Agents 7 notes
- Multi-Agent Systems 5 notes
- Model Routers 4 notes
- Task Planning 2 notes
18 subjects in this area
- Cognitive Models and Latent Representations 20 notes
- Mechanistic Interpretability 19 notes
- LLM Architecture 19 notes
- LLM Memory 19 notes
- Novel LLM Architectures 16 notes
- Reasoning Critiques 14 notes
- Reasoning Architectures 14 notes
- Looped Models 11 notes
- Chain-of-Thought and Reasoning Methods 10 notes
- Logical Reasoning and Internal Rules 10 notes
- Diffusion-Based LLMs 9 notes
- Multimodal Models 7 notes
- Correct but Not Understood 7 notes
- Context Engineering 5 notes
- Mobile and On-Device LLMs 4 notes
- Reasoning by Reflection and Self-Critique 2 notes
- World Models 1 note
- Foundation Models 1 note
11 subjects in this area
- Reinforcement Learning 38 notes
- RL with Verifiable Rewards (RLVR) 32 notes
- Test-Time Compute 24 notes
- Training and Fine-Tuning 18 notes
- Self-Refinement and Self-Consistency 14 notes
- Reasoning Model Architectures 14 notes
- Reward Models 9 notes
- Deep Research Agents 8 notes
- Evolutionary Methods 3 notes
- Inference-Time Scaling 3 notes
- Training Data 3 notes
5 subjects in this area
5 subjects in this area
7 subjects in this area
6 subjects in this area