Browsed by
[Tag:] AI

The role of MessagesPlaceholder in LangChain.js

The role of MessagesPlaceholder in LangChain.js

Comments 0 Comment

The MessagesPlaceHolder in LangChain.js plays a crucial role in enabling dynamic and flexible construction of chat prompts by acting as a placeholder for a list of messages within a ChatPromptTemplate. Its primary functions are Dynamic Message Insertion It allows you to inject a list of BaseMessage objects (like HumanMessage, AIMessage, SystemMessage, etc) into a specific position within your chat prompt template during runtime. This is particularly useful for managing chat history, where the list of past messages needs to be…

Read More Read More

Perverse Incentives

Perverse Incentives

Comments 0 Comment

Many AI coding assistants, including Claude Code, charge based on token count – essentially the amount of text processed and generated. This creates what economists would call a “perverse incentives(삐뚤어진 유인책)” – an incentive that produces behavior contrary to what’s actually desired. Let’s break down how this works: It might be difficult for AI companies to prioritize code conciseness when their revenue depends on token count. There’s clearly something going on where the more verse the LLM is, the better…

Read More Read More

A.I. 시대에 소프트웨어 개발이란?

A.I. 시대에 소프트웨어 개발이란?

Comments 0 Comment

2022년 11월 ChatGPT가 본격적인 A.I.의 서막을 알렸으니 A.I. 붐이 일어난지 아직 3년이 채 못 된 시점이다. 비록 짧은 기간이지만 근래 우리 피부에 와닿는 이 기술의 파급력은 어마어마하다. 초기 그렇게 덩치가 컸던 A.I. 모델도 3년도 안돼 휴대폰 속까지 들어와버렸으니 A.I.를 모르는 사람은 거의 없을 지경이다. 이렇게 전 세계적으로 파급력도 크고 전파력도 강한 A.I.가 일상생활 속에서 느끼는 체감이 이정도인데 이 업계에 몸담고 있는 나로서는 오죽하겠는가! A.I.가 만들어 내는 결과물을 접하는 이용자의 시각과 A.I.를 활용해 결과물을 만들어 내는 개발자의 입장에서 바라보는 관점은 사뭇…

Read More Read More

Langgraph – Edges

Langgraph – Edges

Comments 0 Comment

Edges define how the logic is routed and how the graph decides to stop. This is a big part of how your agents work and how different nodes communicate with each other. There are a few key types of edges: A node can have MULTIPLE outgoing edges. If a node has multiple out-going nodes, all of those destination nodes will be executed in parallel as a part of the next superstep.

LLM Based Agent

LLM Based Agent

Comments 0 Comment

“A little piece of advice. You see an agent, you do what we do. Run!” – Cypher to Neo in the movie, “The Matrix” When it comes to LLM-based agents, there is no universally accepted definition, but we can extend the philosophical definition to say that an agent is an intelligent(?) entity that leverages LLMs to solve complex tasks by interacting with the environment via a set of tools. Since LLMs possess good understanding, reasoning & generation capabilities, it makes…

Read More Read More

OpenAI Unveils Technology That Can ‘Reason’ With Images

OpenAI Unveils Technology That Can ‘Reason’ With Images

Comments 0 Comment

The company also introduced a new tool that helps computer programmers use chatbots when writing code. In September(2024), OpenAI introduced A.I. technology that could “reason” through tasks involving math, coding and science. Now, this technology can tackle similar tasks that involve images, including sketches, posters, diagrams and graphs. On Wednesday(2025.4.16), the company unveiled two new versions of its reasoning technology called OpenAI o3 and OpenAI o4-mini. Each can handle tasks that involve both images and text. These systems can “manipulate, crop and…

Read More Read More

Turing Award Goes to 2 Pioneers of Artificial Intelligence

Turing Award Goes to 2 Pioneers of Artificial Intelligence

Comments 0 Comment

Andrew Barto and Richard Sutton developed reinforcement learning, a technique vital to chatbots like ChatGPT. In 1977, Andrew Barto, as a researcher at the University of Massachusetts, Amherst, began exploring a new theory that neurons behaved like hedonists. The basic idea was that the human brain was driven by billions of nerve cells that were each trying to maximize pleasure and minimize pain. A year later, he was joined by another young researcher, Richard Sutton. Together, they worked to explain human…

Read More Read More

AI systems based on two model types

AI systems based on two model types

Comments 0 Comment

The current frontier of AI systems is based on two model types(they are almost identical under the hood, but their behavior is notably different in practice, hence the distinction) Pre-trained models, also known as ‘non-reasoning models’ These are the famous ‘Large Language Models’, or LLMs, gigantic AI models trained on as much as data as possible, reaching double digits of trillions of words (for reference, Lama 3.1 405B was trained on 15 trillion tokens ~ 11-12.5 trillion words, and DeepSeek…

Read More Read More

How did DeepSeek build its A.I. with less money?

How did DeepSeek build its A.I. with less money?

Comments 0 Comment

The Chinese start-up used several technological tricks, including a method called “mixture of experts” to significantly reduce the cost of building the technology. A.I. companies typically train their chatbots using supercomputers packed with 16,000 specialized chips or more. But DeepSeek said it needed only about 2,000. DeepSeek engineers needed only about $6 million in raw computing power, roughly one-tenth of what Meta spent in building its latest A.I. technology. What exactly did DeepSeek do? How are A.I. technologies built? Companies…

Read More Read More

DeepSeek just Exposed the Rot at the Core of the AI Industry

DeepSeek just Exposed the Rot at the Core of the AI Industry

Comments 0 Comment

DeepSeek made two critical changes. Firstly. the architecture. OpenAI uses an AI architecture known as “fully dense”. This basically means that the architecture is comprised of a single, vast network that processes every request with all its parameters and data points. This is incredibly computationally dense, but the idea is that it can make it more capable in a broader application. DeepSeek is instead much more picky and uses a “mixture of experts” architecture. In this approach, the AI is…

Read More Read More