人工智能2022 · 分享于 Hacker News
Training language models to follow instructions with human feedback [pdf]
探索《Training language models to follow instructions with human feedback [pdf]》的原文与 Hacker News 社区讨论，查看来源并加入阅读清单。
从论文，走向讨论
看看社区如何讨论这个想法。
来自 Hacker News 的原始讨论。不同的视角、疑问，以及值得继续思考的线索。
最多展示 100 条相关讨论。论文可能出现在评论中，并非原帖投稿内容。
在讨论中发现的引用
按 HN 条目顺序展示最近的 50 条引用来源。
评论 #48420458 评论 #44859864 评论 #40734016 评论 #40550052 评论 #37879724 评论 #36793599 评论 #36419501 评论 #36419491 评论 #36133507 评论 #36099866 评论 #35984584 评论 #35506068 评论 #35262817 评论 #35150646 评论 #35091088 评论 #35028468 评论 #34801934 评论 #34757699 评论 #34658679 评论 #34653841 评论 #34252886 评论 #34111927 评论 #33958938 评论 #33918570 评论 #33342468
Ynick_pou ·
Safe Superintelligence Inc.
1,214 赞同1,068 评论
Yflabber ·
Curious about the training data of OpenAI's new GPT-OSS models? I was too
239 赞同57 评论
Yingve ·
LLMs aren't "trained on the internet" anymore
193 赞同109 评论
Yraldi ·
GPT-3 can create both sides of an Interactive Fiction transcript
132 赞同68 评论
Ytaytus ·
GPT-4 is getting worse over time, not better
88 赞同55 评论
Ygardenfelder ·
The LLama Effect: Leak Sparked a Series of Open Source Alternatives to ChatGPT
58 赞同7 评论
Yaaronrelph ·
Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA
23 赞同2 评论
Yjasonhansel ·
Announcement: AI generated answers are officially banned here
22 赞同7 评论
Ywashedup ·
What Is ChatGPT Doing and Why Does It Work?
16 赞同8 评论
Yjamespwilliams ·
ChatGPT, Rot13, and Daniel Kahneman
14 赞同9 评论
Ygeorgehill ·
GPT-4 is coming next week – and it will be multimodal, says Microsoft Germany
8 赞同2 评论
Ygtsnexp ·
Ask HN: What dataset was used to train ChatGPT? How can we find out?
3 赞同1 评论
Yjosefslerka ·
Training language models to follow instructions with human feedback [pdf]
3 赞同0 评论
Ytosh ·
Training language models to follow instructions with human feedback
2 赞同0 评论
Ynadermx ·
The paper that made ChatGPT possible
2 赞同0 评论
Ypps ·
Open Assistant – project meant to give everyone access to a great chat based LLM
2 赞同1 评论
Y7moritz7 ·
I made ChatGPT and Bing AI have a conversation
2 赞同1 评论
Yscraptor ·
Lawyer cites fake cases invented by ChatGPT, judge is not amused
2 赞同0 评论
YGarcia98 ·
Chain-of-Thought Hub: Measuring LLMs' Reasoning Performance
2 赞同0 评论
Ynatolambert ·
How RLHF Works
2 赞同0 评论
Ygnicholas ·
A New Chat Bot Is a ‘Code Red’ for Google’s Search Business
1 赞同0 评论
Ysillysaurusx ·
Show HN: Llama-dl – high-speed download of LLaMA, Facebook's 65B GPT model
1 赞同0 评论
Ygeorgehill ·
Microsoft lays off an ethical AI team as it doubles down on OpenAI
1 赞同0 评论
Ytosh ·
Training language models to follow instructions with human feedback
1 赞同0 评论
Yhighfrequency ·
Has ChatGPT Been Neutered?
1 赞同0 评论
Yspdustin ·
All of ChatGPT's System Prompts
1 赞同0 评论
Yandrehacker ·
What was your "Oh Shit" moment with GenAI?
1 赞同1 评论