JaesungPark

<조달청 나라장터 & Foundry, AIP> 안녕하세요! Foundry, AIP를 공부하는 겸 만들고 있는 사이드프로젝트를 공유드려봅니다. 나라장터 API를 통해 입찰공고, 개찰 데이터를 온톨로지로 가져왔습니다. 입찰공고 마다 첨부되어 있는 hwp 파일들을 가져와 AIP를 통해 hwp 파일내에 명시되어 있는 과업…

개인 AIP Developer Tier 계정 생성이 한국에서도 가능하네요! 북미 / 유럽 지역 국가에서만 지원했던 것으로 기억하는데 이제 한국이 지원 국가에 포함되어 있습니다.

BUILD WARS LIVE : Brett + Webflow vs. Henrik + Lovable (Sponsored by Paper and Contra) x.com/i/broadcasts/1…

⚡️ 523-Mile Hydrogen-Electric Flight ⚡️ We've accomplished something many thought impossible: flying more than 500 miles with no in-flight emissions except water, including a vertical take-off and landing.

I hate opening multiple browser tabs for each work tool when I work. Switching to Notion, Google Drive, Jira, etc... is annoying. Now building vecpot.com to search and access in one place. What do you think? cc @_buildspace @_nightsweekends

How to train your own Large Language Models This is a great article on the mechanics of training (your own) large language models. Discusses the importance of training your own LLM, data pipelines, model training, evaluation, and deployment. blog.replit.com/llm-training

Watching a talk on *LLM evaluation* organized by Langchain, featuring guests from OpenAI and Anthropic. Main takeaways: (1/11)

💡Question Generation for LLM Evaluation 🔬 We present a method to easily generate a dataset of evaluation questions from a given text corpus. You can evaluate retrieval-augmented generation over these questions - no ground-truth required!