Yoonicorn[논문 리뷰] “Do Anything Now”: Characterizing and Evaluating In-The-Wild Jailbreak Prompts on LLM(2023)개요39 min read·3 days ago----
Yoonicorn2024년 LLM 핵심 개념 RAG: RAG란 무엇일까?안녕하세요! 최근에 RAG의 중요성에 대해 현업에서 많이 체감하고 있습니다.6 min read·May 10, 2024----
YoonicornPEFT(효율적 파라미터 파인 튜닝) 활용한 성능 최적화: 프롬프트 튜닝 딥다이브이 게시글은 2023년 11월 27일 Akriti Upadhyay가 medium에 게재한 “Optimizing Performance with PEFT: A Deep Dive into Prompt Tuning” 글에 대한 번역과 함께 첨언한 내용임을…28 min read·Dec 13, 2023----
Sona[논문리뷰] 랭체인관련 논문 — ReAct: Synergizing Reasoning and Acting in Language Models (간단한 실습 w.pytorch)선행지식: LangChain에 대한 전반적인 흐름, 구조 (prompt, llm model, agents, tools etc…)8 min read·Oct 16, 2023----
![[논문 리뷰] “Do Anything Now”: Characterizing and Evaluating In-The-Wild Jailbreak Prompts on LLM(2023)](https://miro.medium.com/v2/resize:fill:160:106/0*IUlCdu7HVcxUwzG7.png)
![[논문 리뷰] “Do Anything Now”: Characterizing and Evaluating In-The-Wild Jailbreak Prompts on LLM(2023)](https://miro.medium.com/v2/resize:fill:320:214/0*IUlCdu7HVcxUwzG7.png)
![[Trustworthy AI] 적대적 공격에 대응해 AI 안전성 확보하기](https://miro.medium.com/v2/resize:fill:160:106/1*gEvT-DsjeOJm9cUvTZsT2A.png)
![[Trustworthy AI] 적대적 공격에 대응해 AI 안전성 확보하기](https://miro.medium.com/v2/resize:fill:320:214/1*gEvT-DsjeOJm9cUvTZsT2A.png)
![[논문리뷰] 랭체인관련 논문 — ReAct: Synergizing Reasoning and Acting in Language Models (간단한 실습 w.pytorch)](https://miro.medium.com/v2/resize:fill:160:106/0*xXI8SB73IqFFlk0r.png)
![[논문리뷰] 랭체인관련 논문 — ReAct: Synergizing Reasoning and Acting in Language Models (간단한 실습 w.pytorch)](https://miro.medium.com/v2/resize:fill:320:214/0*xXI8SB73IqFFlk0r.png)
