Discover

Learned Sparse Retrieval, Neural IR, Sparse Embeddings

reinforcement learning human feedback, preference learning, reward modeling, DPO

RAG, Dense Retrieval, Hybrid Search, Reranking

Qwen, Alibaba LLM, Qwen2, open source model

program synthesis, sketch, deductive synthesis, inductive programming

ML engineer, model deployment, production ML, machine learning systems

local LLM, on-device AI, edge inference, private AI, self-hosted models

LLM benchmarks, model evaluation, evals, red-teaming, agent assessment

generative AI, ChatGPT, LLM, GPT-4, foundation models

Claude code plugins, skills, and commands

artificial intelligence, AI industry, AI announcements

mechanistic interpretability, explainable AI, XAI, saliency

Value Learning, RLHF, Constitutional AI, Safety Research

multi-agent systems, LLM orchestration, agent pipelines, AutoGen, CrewAI

agent memory architecture, context window, episodic memory, working memory AI

AI Agents, Autonomous Reasoning, Multi-agent Coordination, Tool Use

attention mechanism, self-attention, transformers, encoder decoder

reinforcement learning, reward, policy gradient, Q-learning