I previously wrote about Sayonara, Prompt Engineering. Prompts for an LLM are best known to the LLM itself, and each LLM has its own optimal hyper-parameters, so it's not really suitable for ordinary, everyday users to keep learning and matching all of that themselves every single time.
사요나라, 프롬프트 엔지니어링
open ai 가 쏘아올린 chat gpt 열풍으로.. 프롬프트 엔지니어이라는 새롭게 창직?된 직업군이 있다. 생성형 인공 지능(생성형 AI) 솔루션을 안내하여 원하는 결과를 생성하는 프롬프트 엔지니어링 프
normalstory.tistory.com
More importantly, OpenAI is not yet the standard for LLMs. This market is just at the introduction stage. Personally, I think OpenAI resembles a PDA phone right before the smartphone era. Its interface and ecosystem, in spite of the original intent, are closed and cloud-based, so they depend on an online environment. On top of that, it has not yet fused with personal devices. There are also many other issues like security.
Personally, I think Apple, which built a software ecosystem on a hardware base, or Google, Amazon, and Tesla, which are building hardware ecosystems on a software base, are likely to be the main players.
So in the middle of these mega-trends and the moves of the big brothers, what should the individual be preparing?!
Rather than optimizing prompts, you should be thinking about your own agent.
In that sense, there is a basic term you should know — namely MoE, mixture of experts. For detailed explanations there are plenty of articles by experts in Korea and abroad if you Google it, so I'll just briefly summarize the basics here.
Terminology
MoE is an architectural pattern in neural networks that divides the computation of a single layer or operation (for example, a linear layer, an MLP, or attention projection) into multiple "expert" sub-networks. These sub-networks each independently perform their own computation, and their results are combined to produce the final output of the MoE layer. An MoE architecture can be either dense (where every expert is used for every input) or sparse (where only a subset of experts is used for each input).
Subjective interest
My personal interest in MoE is not a single, more-performant model, but rather an approach for organizing a collection of models that can collaborate and divide labor. Sometimes they are called agents, sometimes experts. I had the thought that this trend has a similar shape to how blockchain consensus algorithms (POW, POS, DPOS, POI, POC, etc.) — once?, after countless human trial and error — have come to resemble the consensus structures of evolving institutions and norms. If humans benchmark nature to advance science, then IT technologies like AI and blockchain seem to be increasingly imitating human institutions to advance themselves, forming a kind of loop. That's why I keep an eye on the relevant developments.
Subjective references
In the MoE architecture, the emphasis is on collaboration through organization and consensus structures. From the perspective not of a developer but of service planning, the point is how seamlessly you can organize collaboration between agents, collaboration with the individual, and the individual's creation of agents.
The MoE architect focuses on collaboration through organizational and consensus structures. From a service planning perspective, it is about how seamlessly you can organise collaboration between agents, collaboration with individuals and the creation of agents for individuals.
Related technical trends with similar concepts are evolving fast. Even though the Why and the How are the same, the What — that is, the way they are delivered, and the terminology — is all over the map. Let me organize a few products (sometimes a model, sometimes a framework, etc.) that share a similar architecture.
#Chunking Strategies: Agentic Chunking
https://normalstory.tistory.com/entry/RAG-Agentic-Chunking-ing
LLM | Five Levels of Chunking( 스압 주의!)
1. 개요 Chunking Chunking은 고품질의 응답에 많은 영향을 미치는 중요한 과정으로써 텍스트를 관리를 쉽고, 명확하게 중요한 부분으로 나누는 과정으로 맥락의 효율적인 처리와 검색을 위해 사용" data-og-host="normalstory.tistory.com">
normalstory.tistory.com
#Optimization at the in-model unit-process level
LangGraph - Building language agents as graphs
GitHub - langchain-ai/langgraph
Contribute to langchain-ai/langgraph development by creating an account on GitHub.
github.com
llamaindex - Agentic strategies
Agentic strategies - LlamaIndex ? v0.10.17
Previous Context-Augmented OpenAI Agent
docs.llamaindex.ai
Tencent - More Agents Is All You Need
GitHub - MoreAgentsIsAllYouNeed/More-Agents-Is-All-You-Need
Contribute to MoreAgentsIsAllYouNeed/More-Agents-Is-All-You-Need development by creating an account on GitHub.
github.com
#General-purpose, abstraction-based frameworks
AutoGen - A programming framework for agentic AI.
GitHub - microsoft/autogen: A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/
A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap - microsoft/autogen
github.com
Crew AI - Multi AI Agents systems
GitHub - joaomdmoura/crewAI: Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intellig
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. - joaomdmoura/cr...
github.com
#Code-generation optimization
Devika - Agentic AI Software Engineer
GitHub - stitionai/devika: Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break th
Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective...
github.com
