์ฃผ๋ฏผ๊ฑด
๊ธฐ๋ก = ์ฑ์ฅ
TestingLLM/ChatGPT_NER.ipynb at main ยท ritun16/TestingLLM
Contribute to ritun16/TestingLLM development by creating an account on GitHub.
ritun16Trends in AIโโโMarch 2023
LLaMA from Meta, an embodied PALM-E model from Google, and Consistency Models, and new OpenAI API endpoints plus a juicy pricing forโฆ
Sergi Castella i Sapรฉ
Introduction to Reinforcement Learning with Human Feedback
Learn about reinforcement learning with human feedback (RLHF) โ a new technique for training large language models that has been behind many of the major advances in OpenAIโs ChatGPT and InstructGPT LLMs, DeepMindโs Sparrow, Anthropicโs Claude, and more.
Edwin Chen
GitHub - microsoft/JARVIS: JARVIS, a system to connect LLMs with ML community
JARVIS, a system to connect LLMs with ML community - GitHub - microsoft/JARVIS: JARVIS, a system to connect LLMs with ML community
microsoftGitHub - Kent0n-Li/ChatDoctor
Contribute to Kent0n-Li/ChatDoctor development by creating an account on GitHub.
Kent0n-LiColossalChat: An Open-Source Solution for Cloning ChatGPT With a Complete RLHF Pipeline
Large AI models and applications like ChatGPT and GPT-4 have become extremely popular worldwide, serving as a foundation for theโฆ
Yang You
ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks ๐ Key insights/lessons learned: - The study shows that...
Posted by Daily Arxiv on Monday, March 27, 2023
์ปดํจํ
์ฌ๊ณ ์ ๊ฐ๋ฐ ์ค๋ ฅ ๋๋ฆฌ๋ ๊ณต๋ถ๋ฒ | ์์ฆIT
์ด๋ฒ ๊ธ์ ๊ฐ๋ฐ ์ค๋ ฅ์ ๋๋ฆฌ๊ธฐ ์ํ ๋ฐฉ๋ฒ๊ณผ ์ปดํจํฐ์ ์ผ๋ก ์ฌ๊ณ ํ๋ ๋ฒ์ ๋ํ ๊ฐ์ธ์ ์ธ ๊ณ ์ฐฐ์ ๊ดํ ๊ธ์
๋๋ค. ์ด๋์ด๋ผ ์๊ฐํ๊ณ ๊พธ์คํ ํ๋ จํ๊ธฐ, ์๊ตฌ์ฌํญ์ ๋ฐ์ดํฐ ๊ด์ ์ผ๋ก ์ฌ๊ณ ํ๊ธฐ๋ผ๋ ํต์ฌ ์ฒ ํ์ ๋ฐํ์ผ๋ก ์ด๋ป๊ฒ ํ๋ฉด ๊ฐ๋ฐ ์ค๋ ฅ์ ํจ๊ณผ์ ์ผ๋ก ํค์ฐ๊ณ , ์ปดํจํฐ์ ์ผ๋ก ์๊ฐํ๊ฒ ํ ์ ์์์ง์ ๋ํด ์๊ธฐํ๋ ค๊ณ ํฉ๋๋ค. ์ด ๊ธ์ด ๊ฐ๋ฐ ์ค๋ ฅ์ ๋๋ฆฌ๊ณ ๋์๊ฒ ๋ง๋ ๊ณต๋ถ๋ฒ์ ์ฐพ๋ ๋ฐ ๋์์ด ๋๊ธฐ๋ฅผ ๋ฐ๋๋๋ค.
Wishket Inc,.
The Dark Side of LLMs: We Need to Rethink Large Language Models
We cannot deploy the current crop of LLMsย safely
Kai Greshake
How does ChatGPT retain the context of previous questions?
One of the innovations with OpenAIโs ChatGPT is how natural it is for users to interact with it.What is the technical enabler for ChatGPT to maintain the context of previous questions in its answe...
milez
GitHub - Beomi/KoAlpaca: KoAlpaca: Korean Alpaca Model based on Stanford Alpaca (feat. LLAMA and Polyglot-ko)
KoAlpaca: Korean Alpaca Model based on Stanford Alpaca (feat. LLAMA and Polyglot-ko) - GitHub - Beomi/KoAlpaca: KoAlpaca: Korean Alpaca Model based on Stanford Alpaca (feat. LLAMA and Polyglot-ko)
BeomiFive mistakes to avoid when modeling with imbalanced datasets
And what to try instead
Phillip Chilton AdkinsHow to use ChatGPT in product management
What is ChatGPT, prompting tips, and use cases in product management
Guodong (Troy) ZhaoA Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need? ๐ฃ Summary As ChatGPT goes...
Posted by Daily Arxiv on Saturday, March 25, 2023
์ธ๊ณต์ง๋ฅ ์ฑGPT์ ๋์๋ ์งํ!...์์ดํฐ ์ฑ์คํ ์ด, ๊ตฌ๊ธ ํ๋ ์ด ๋์ด โLLM ์ฑ ์คํ ์ดโ ์๋ ์ด์๋ค!
์์ดํฐ ์ฑ์คํ ์ด๋ ๊ตฌ๊ธ ํ๋ ์ด ์คํ ์ด์ฒ๋ผ ์ด๋ค ์ฑ์ด ํ์ํ๋ฉด ์ฑ ์คํ ์ด ๋ค์ด๊ฐ์ ๊ฒ์ํด์ ๋ค์ด๋ฐ๊ณ ๊ทธ ์ฑ์ ์ฌ์ฉํ๋ฏ ์ด์ , ์ธ๊ณต์ง๋ฅ ์ฑGPT์์๋ ํ๋ฌ๊ทธ์ธ์ ํตํด ๊ฐ๋ฐ์๊ฐ ์ ์ํ API์ ์ํธ ์์ฉํ์ฌ ChatGPT์ ๊ธฐ๋ฅ์ ํฅ์ํ๊ณ ๋ค์ํ ์์
์ ์ํํ ์ ์๋ค.๋ค์ ๋งํด, ์๋ ํํฐ(Third Party)๊ฐ ์ฐธ์ฌํ ์ ์๋ ํ์ ChatGPT ์์ ๊น์์ค ๊ฒ์ผ๋ก โ๋ํ์ธ์ด๋ชจ๋ธ ์ฑ ์คํ ์ด(LLM App Store)โ๋ฅผ ํ์์ํจ ๊ฒ์ด๋ค.์ด๋ฅผ ํตํด(ํ๋ฌ๊ทธ์ธ) ChatGPT๋ ์ค์๊ฐ ์ ๋ณด ๊ฒ์(์คํฌ์ธ ์ ์, ์ฃผ๊ฐ, ์ต์ ๋ด์ค ๋ฑ)๊ณผ ์ง
ChatGPT Plugin์ด ๋์๋ค๋๋ฐ ๋ฐ๋ชจ๋ ๋ค๋ฅธ ๋ถ๋ค ๊ธ๋ง ๋ณด๊ณ ๋ ์ค์ ๋ก ์ด๋ป๊ฒ ๋์ํ๋ค๋ ๊ฑด์ง๊ฐ ์ ์๋ฟ์ง ์์ docs๋ฅผ...
Posted by ๊นํ๊ธธ on Friday, March 24, 2023
์ ์ ๊ณจ๋ผ์ ์๋คยท๋ธ ์ ํโฆ๋
ผ๋์ ๊ธฐ์ ๋์๋ค
์๋ช
์ค๋ฆฌ ๋
ผ๋์ ๋ถ๋ฅผ ๋งํ ์ธ๊ณต์์ ๊ธฐ์ ์ด ๋์๋ค. ๋ฏธ๊ตญ ๋ด์์ ์จ์ผ์ฝ๋ฌ์๋ ์ฐ๊ตฌ์ง์ ๋ถ์์น๋ฃ๋ฅผ ๋ฐ๋ ๋ถ๋ถ๊ฐ ์๊ธฐ์ ์ฑ๋ณ์ ์ ํํด์ ์์ ๋ฐ์ ์ ์๋ ์ธ๊ณต์์ ๊ธฐ์ ์ ๊ฐ๋ฐํด ์์ ํ ๊ฒฐ๊ณผ๋ฅผ ๊ณต๊ฐํ์ ์ง โํ๋ก์ค ์โ์
ํ์ข
์ ๊ณต๋ณ ํ๊ตฌ ์ฃผ์ 
์ค๋์ ChatGPT plugins์ ์ฅ๋ฉด์ ์์ถ์ ์ผ๋ก ์ค๋ช ํ๋ ํธ์์ด๋ค์. ๋ฏธ์ฒผ ํ์๋ชจํ HashCorp ์ฐฝ๋ฆฝ์(Terraform ๋ง๋๋)์ ํธ์์ ๋๋ค. ๋ฐ๋ชจ ์์์ ๋ง์ง๋ง์ด ์ด ์ด์ผ๊ธฐ์์ต๋๋ค. ์์์ 1ํ ๋ดค์...
Posted by ์ต์น์ค on Friday, March 24, 2023
Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback ๐ฃ...
Posted by Daily Arxiv on Friday, March 24, 2023
https://www.linkedin.com/pulse/prompt-leakage-์ฃผ์๋ณด-artificial-society/
GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models ๐ฃ Summary The paper examines...
Posted by Daily Arxiv on Monday, March 20, 2023
