Topics to learn, explore and remember.
Up next:
- Amazon interview prep
- Absolute Zero: Reinforced Self-play Reasoning with Zero Data
- PPO / DAPO / GRPO
- Verl
- Training Large Language Models to Reason in a Continuous Latent Space
- Monolith
- SIMA & paper
- Competitive Programming with Large Reasoning Models
- Physical Intelligence
- Flink
- Kafka
- https://sam2act.github.io/
- https://www.latent.space/p/2025-papers
- https://lilianweng.github.io/posts/2020-01-29-curriculum-rl/
- https://digitalhumanity.substack.com/p/project-sid-many-agent-simulations
- paper^
- Multi Agent Reinforcement learning
- Manufacturing
- Biggest things that contributed to industrial revolution
- What worked in industry
- Scaling laws
- KV caches
- Different types of Attention
- Ranking
- Recomendation Systems
- Ads
- Emergence - higher order behaviors from smaller minimal behavior
- History of optimization algorithms - genetic algo, Operational research
- Recent LLM Breakthroughs
- Clustering
- DS Concepts
- Search
- UCB
- Prob graphical models
- GNN
- ALL recent OpenAI, Deepseek, Mistral, … Papers