Engineering Notes

Engineering Notes

Thoughts and Ideas on AI by Muthukrishnan
Tags - Engineering Notes

Tags

ai agents90 engineering-management57 ai26 reinforcement learning23 planning19 multi-agent-systems15 tutorial14 llms13 multi-agent12 python12 langgraph9 llm9 agentic-ai8 autonomous agents8 architecture7 decision-making7 reasoning7 algorithms6 coding5 development5 game theory5 machine learning5 tool-use5 alignment4 deep-research4 orchestration4 rag4 research4 testing4 ai safety3 coordination3 crewai3 memory3 reliability3 scalability3 transfer-learning3 agent-architecture2 autogen2 benchmarking2 context engineering2 distributed computing2 distributed-systems2 evaluation2 exploration2 heuristics2 hierarchical-rl2 hybrid systems2 program-synthesis2 q-learning2 search2 search algorithms2 self-correction2 slms2 software-development2 software-engineering2 swarm intelligence2 uncertainty2 vector databases2 a* algorithm1 active-inference1 actor-critic1 adaptation1 adaptive systems1 adversarial search1 agent training1 agent-safety1 api1 attention-mechanisms1 auction-theory1 autoformalization1 automata1 autonomous-systems1 bandit-algorithms1 batch-rl1 bayesian1 bdi1 behavior trees1 behavioral-cloning1 bellman equation1 c511 catastrophic-forgetting1 causal-inference1 causal-reasoning1 classical-ai1 classical-planning1 claude1 claude-code1 code review1 code-generation1 coding agent1 cognitive science1 collaboration1 communication-protocols1 complexity1 composition1 compositionality1 consensus1 conservative-q-learning1 constitutional ai1 constrained-decoding1 constrained-mdp1 continual-learning1 continuous-control1 control-theory1 conversational ai1 cooperative-ai1 cooperative-game-theory1 corrigibility1 cpo1 credit-assignment1 crew-based1 csp1 curiosity1 curriculum-learning1 dag1 dagger1 debate1 debugging1 decision-theory1 decision-transformer1 deep-learning1 deepeval1 deliberation1 design-patterns1 developer-workflow1 devops1 diffusion-models1 distributed ai1 distributional-rl1 dpo1 dspy1 dyna1 dynamic programming1 embeddings1 embodied-ai1 emergence1 emergent-behavior1 entropy-regularization1 error-handling1 ethics1 fairness1 fault-tolerance1 few-shot-learning1 formal-methods1 frameworks1 free-energy1 function calling1 future1 game-ai1 generative-ai1 goal-conditioned1 goap1 google adk1 grounding1 her1 heuristic-search1 hierarchical planning1 htn1 human-in-the-loop1 ide1 imitation-learning1 information retrieval1 intent-classification1 interactive-systems1 interoperability1 interruptibility1 intrinsic-motivation1 inverse-rl1 knowledge-distillation1 knowledge-representation1 lagrangian1 language-models1 learning1 learning-from-demonstrations1 lifelong-learning1 marl1 maximum-entropy1 mcp1 mcts1 mean-field-games1 memory systems1 meta-cognition1 meta-learning1 meta-programming1 metrics1 mmlu1 model-based1 model-compression1 monitoring1 nash equilibrium1 neural-networks1 neural-symbolic1 neuroscience1 nlp1 o11 observability1 offline-rl1 openai1 opponent-modeling1 optimization1 options-framework1 paired1 parallelism1 pathfinding1 pddl1 perception1 pipelines1 plr1 plugin architecture1 poker1 policy-gradients1 pomdps1 preference-learning1 problem solving1 prompt chaining1 prompt-optimization1 prompting1 qr-dqn1 quality-assurance1 react1 recursive-reasoning1 reflexion1 repl1 resilience1 retrieval1 reward engineering1 reward-learning1 reward-machines1 reward-modeling1 risk-sensitive1 rlhf1 robotic-planning1 robotics1 role-specialization1 saas1 sac1 safety1 sample-efficiency1 scaling1 scaling laws1 self-improvement1 self-organization1 self-play1 self-refinement1 semantic search1 semantic-routing1 shapley-values1 skill-learning1 soft-actor-critic1 source-control1 sparse-rewards1 spec-driven-development1 specialization1 stanford1 startups1 state-management1 strategy1 strips1 structured-output1 subgoals1 subscription platform1 successor-representations1 swarm1 swe-agent1 symbolic ai1 symbolic-reasoning1 system design1 systems-architecture1 task decomposition1 task-allocation1 task-scheduling1 task-specification1 td learning1 temporal-abstraction1 test-time compute1 theory-of-mind1 training1 trajectory-optimization1 transformers1 tree of thoughts1 validation1 value functions1 vector embeddings1 verification1 vision-language1 windsurf1 workflow1 workflow-orchestration1