AI BriefingKakao news
The latest AI and developer news from Kakao, with short summaries.
Visit website →MySQL 9.0 Enforces caching_sha2_password as Default Authentication, Deprecates mysql_native_password
Support for mysql_native_password is discontinued in MySQL 9.0, making the transition to caching_sha2_password and preparation for SSL/RSA connections essential.
Kakao Moves Beyond Vibe Coding to Agentic Coding Experiments, Achieving 2x Productivity Gains
Kakao has validated an average 2x productivity improvement and production-grade code quality through the adoption of AI coding agents.
Building an AI Judging System for a 250-Person Hackathon in 48 Hours with Vibe Coding
Using vibe coding, an AI judging system for a 250-person hackathon was built in just 48 hours.
Kakao Presents HG-DPO Paper for Person Image Generation at CVPR 2025
The HG-DPO study, which improves person generation quality by applying three-stage Curriculum Learning that uses real-world data as Winning images, was selected as a highlight paper at CVPR 2025.
Kakao Hosts Internal Hackathon '10K' with Vibe Coding; Participation Across All Roles Up 50%
Development time was reduced to 10 hours and AI judging was introduced, with 250 participants from all job roles.
Kakao Open-Sources 'Kanana Safeguard' Series of Korean-Specialized AI Guardrails
Kakao has open-sourced the 'Kanana Safeguard' series, consisting of three AI guardrail models specialized for Korean user environments, under the Apache 2.0 license.
Kakao Releases Commercially Usable Open-Source LLM 'Kanana 1.5'
Kakao has released Kanana 1.5 8B and 2.1B models under the Apache 2.0 license, allowing for commercial use.
Kakao Releases Open-Source 'Kanana 1.5' for Agentic AI with Major Math and Coding Enhancements
Kakao has open-sourced the 'Kanana 1.5' 8B and 2.1B models under the Apache 2.0 license, enhancing math and coding performance and long-context understanding to support Agentic AI.
Comparative Analysis of MySQL ALTER DDL Algorithm Mechanics and Metadata Locks
This analysis compares the operational principles of MySQL's Copy, In-Place, and Instant ALTER DDL algorithms and their Metadata Lock acquisition patterns.
Kakao Unveils Multimodal LLM 'Kanana-o' Integrating Voice and Vision via Model Merging
Kakao has released 'Kanana-o', a multimodal LLM that integrates its voice model (Kanana-a) and vision model (Kanana-v) using model merging techniques, demonstrating superior performance compared to global models in Korean speech recognition (CER 8.5).
A Non-Developer's Vibe Coding Experience: Leveraging LLMs and AI Agent Tools
A non-developer shared their vibe coding experience of building rule-based HTML tools to reduce LLM uncertainty and automating repetitive tasks using AI agents.
Kakao Developer Tests Vibe Coding: Successfully Implements Web Project in 6 Hours
Wrote 1,500 lines of code in 6 hours using Cursor and Claude 3.7, but concluded that complete replacement is impossible
Vibe Coding Guide for the AI Agent Era: How to Use Cursor, Copilot, Claude Code, and Codex CLI
This article explains the concept of vibe coding proposed by Andrej Karpathy and the importance of prompt engineering, comparing the features and use scenarios of four AI coding tools: Cursor, GitHub Copilot Agent, Claude Code, and OpenAI Codex CLI.
AI Native Development for Non-Developers: 'Waiting is Faster than Learning'
Highlights how the quality of outputs has surged without changes in prompting skills due to advancements in LLM and agent technologies.
Kakao Reveals Vibe Coding Experiment Results: 2x Productivity Boost in Production
In experiments targeting the OLIVE platform, tasks were completed in less than half the estimated time while maintaining verified quality.
Iceberg Log Loading Strategy: DB Uses UPSERT, Server Logs Test APPEND with zstd Level 9 Reducing File Size by 51.4%
In server log Iceberg APPEND loading tests, applying zstd level 9 reduced file size by 51.4% compared to ORC.
Iceberg Operations Journey: Insights for DB and Server Logs
Shares operational experience and insights gained from adopting Apache Iceberg for DB and server log management.
GitHub CEO Visits KakaoTech, Shares Copilot Phase 2 Roadmap and AI Agent Strategy
GitHub CEO Thomas Dohmke visited KakaoTech to share Copilot's 2025 roadmap and AI agent strategy, discussing developer competencies in the AI era.
Kakao Tech Blog Roundup for Q1 2025
Kakao Tech has compiled its major technical blog posts on LLM performance evaluation and AI agents published in Q1 2025.
Kakao Introduces LLM as a Judge for CodeBuddy Performance Evaluation… Proposes Bias Mitigation Strategies
Kakao CodeBuddy utilizes LLM as a Judge for performance evaluation, proposing methods to enhance evaluation reliability by improving prompt structure and mitigating position bias.