-
KT
- Seoul, Republic of Korea
-
21:26
(UTC +09:00) - in/daehee-kim-174132185
Stars
Evaluating LLMs Through Multi-Turn Legal Consultation
✂️ Generates an image from a DOM node using HTML5 canvas and SVG.
A benchmark built to evaluate and improve agent capabilities for supporting legal work.
Skills for Real Engineers. Straight from my .claude directory.
LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐
Complete TypeScript source code of the Claude Code CLI, reconstructed from source maps and runnable locally.
Behavior-Aware Item Modeling (BAIM): procedural representations for knowledge tracing with adaptive multi-stage reasoning (ACL Findings 2026).
"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
한국인을 위한 스킬 모음집 - SRT, KTX, 카카오톡, 한글과컴퓨터, 날씨, 미세먼지, 법령, 주식정보, 조선왕조실록, KBO, K-리그, LCK, 특허 검색, 토스 증권, 맞춤법 검사, 중고차 가격, 쿠팡, 네이버 블로그, 다이소, 올리브영, 택배 송장 조회 등등...
A free and unlimited API for Google Translate 💵🚫
Optimize prompts, code, and more with AI-powered Reflective Text Evolution
JavaScript in-page GUI agent. Control web interfaces with natural language.
ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Repo for "Adaptation of Agentic AI"
Official repository for "Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?" (Findings of ACL 2026)
[WACV'26] Official Pytorch Code for HiMix : Hierarchical Visual-Textual Mixing Network for Lesion Segmentation
Code and data for analyzing investment biases of large language models in finance.
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.