LATEST TECH ARTICLES

Overview: Two Approaches to AI Safety To safely operate chatbots that utilize Large Language Models (LLMs), two primary strategies exist: pre-blocking  and post-monitoring . Pre-blocking  is a method that filters user prompts in advance or applies constraints at the input stage to block risky requests before they are processed by the model. In contrast, post-monitoring  is an approach that supervises and audits the LLM's output in real-time or after the fact to prevent inappr

AI translation solution presented through a real prompter Executive Summary  This Case Study aims to discuss our in-house developed AI-based real-time translation solution designed to overcome communication difficulties in corporate workshops with a multilingual environment. Although the initial model was built upon the OpenAI API, it faced issues with mistranslating company-specific terminology and employee names. To address this, we integrated our independently developed Co

TecAce, an IT company based in Seattle, with 24 years of experience, has changed its vision and business strategy to AI Transformation starting in 2023 and is continuously developing solutions utilizing LLM Foundation and carrying out collaborative projects with partners. In this post, I will share some cases I experienced while developing the AhnLab AI Global Translation Service, which was commercialized in June 2024. CHALLENGE The global professional security company AhnLab

The following text has been translated from Korean to English using AssistAce . Sungjin (James) Kim, Ph.D. | LinkedIn  | YouTube Case Study of Translation LLM Fine-Tuning Introduction The technology of Large Language Models (LLMs) is advancing rapidly. There are various ways to utilize LLMs, including prompting, embedding, and fine-tuning. In this article, we will focus on fine-tuning, which requires a significant amount of GPU computing resources. While it is possible to sec

The following text has been translated from Korean to English using AssistAce . One of the easiest AI solutions to help with LLM (Language Learning Models) these days is the Summary feature. It is a feature useful for its ability to convert long or difficult to understand documents into short and easy to understand content. The feature is already widely utilized and easily accessed to summarize various types of documents such as news, PDFs, webpages, etc. Challenge As seen th

The following text has been translated from Korean to English using AssistAce . What is RAG? The importance of data in the business environment is growing. Companies face many challenges in effectively managing vast data and making strategic decisions based on it. In this situation, the Retrieval-Augmented Generation (RAG) technology is attracting attention. RAG is a form of machine learning that combines data retrieval and information creation to provide more accurate and re

Sungjin (James) Kim, Ph.D. | LinkedIn Table of Contents Introduction The Structure and Operating Principle of the Transformer Encoder Operation Decoder Operation Types and Applications of Transformer-based LLMs Encoder-Only Approach Decoder-Only Approach Encoder-Decoder Approach Latest Methods Implications Introduction Generative AI (GenAI), including Large Language Models (LLMs), has seen significant advancements since the introduction of the transformer architecture[1]. Int

With OpenAI’s late successes and the widespread distribution of their own API, the concept of GPT wrappers has emerged as a popular tool for the tech industry. GPT wrappers are layers of software that provide a more accessible interface to interact with OpenAI's APIs. They simplify the process of integrating AI capabilities into applications, enabling even those with limited AI expertise to leverage the advanced functionalities of models like ChatGPT or DALL-E. With this piec

The technological advancements in Large Language Models (LLM) have established them as a cornerstone technology in various fields such as text generation, translation, and chatbots. Improvements in context understanding and natural language generation abilities, along with the support of fine-tuning APIs and plug-ins, significantly benefit individual creativity and learning. However, the quality evaluation of their outputs remains a critical challenge. This post discusses the

The Early History and Evolution of Machine Translation The history of machine translation technology dates back to the 1940s Cold War era, when the United States and the Soviet Union began developing machine translation technologies to decipher each other's confidential documents. In 1951, Warren Weaver, a researcher in machine translation, was appointed as the chairman of the National Science Foundation (NSF), leading to vigorous development of machine translation technology

AhnLab, a South Korean cybersecurity company, announced on the 31st that it has signed a 'strategic partnership agreement for cloud-based AI transformation and global business' with the U.S.-based AI (Artificial Intelligence) software company TecAce Software, located in the United States, on the 30th. This MOU was made to provide secure and efficient cloud-based AI services and explore joint business opportunities. Through this agreement, both companies plan to collaborate in

Introduction As we venture further into the digital age, the significance of Generative AI, specifically the LLM, in a multitude of sectors cannot be overstated. This cutting-edge technology offers revolutionary solutions for businesses, challenging conventional methods and heralding a new era of efficiency and innovation. From deploying AI-driven customer service chatbots to facilitating advanced data analytics, the introduction of Generative AI underscores its expansive pot

We live in an era overflowing with new information and knowledge. Among them, the ability to find and utilize information that we’re curious about or need is increasingly establishing itself as a crucial competitive advantage. Until recently, we relied on web searches, but now, with the emergence of chatbots based on large language models like ChatGPT (LLM-chatbots), the way we seek information is changing. This is because you can now directly ask LLM chatbots in natural lang

Prompt engineering is a relatively new discipline that has gained prominence in recent years as AI language models have become increasingly prevalent. The practice involves developing and optimizing prompts to efficiently use language models (LMs) for a wide variety of applications and research topics. Prompt engineering skills help to better understand the capabilities and limitations of large language models (LLMs). Prompt engineering is critical for generating high-quality