AI & machine learning2022 · shared on Hacker News
Training language models to follow instructions with human feedback [pdf]
Explore Training language models to follow instructions with human feedback [pdf], its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Comment #48420458 Comment #44859864 Comment #40734016 Comment #40550052 Comment #37879724 Comment #36793599 Comment #36419501 Comment #36419491 Comment #36133507 Comment #36099866 Comment #35984584 Comment #35506068 Comment #35262817 Comment #35150646 Comment #35091088 Comment #35028468 Comment #34801934 Comment #34757699 Comment #34658679 Comment #34653841 Comment #34252886 Comment #34111927 Comment #33958938 Comment #33918570 Comment #33342468
Ynick_pou ·
Safe Superintelligence Inc.
1,214 points1,068 comments
Yflabber ·
Curious about the training data of OpenAI's new GPT-OSS models? I was too
239 points57 comments
Yingve ·
LLMs aren't "trained on the internet" anymore
193 points109 comments
Yraldi ·
GPT-3 can create both sides of an Interactive Fiction transcript
132 points68 comments
Ytaytus ·
GPT-4 is getting worse over time, not better
88 points55 comments
Ygardenfelder ·
The LLama Effect: Leak Sparked a Series of Open Source Alternatives to ChatGPT
58 points7 comments
Yaaronrelph ·
Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA
23 points2 comments
Yjasonhansel ·
Announcement: AI generated answers are officially banned here
22 points7 comments
Ywashedup ·
What Is ChatGPT Doing and Why Does It Work?
16 points8 comments
Yjamespwilliams ·
ChatGPT, Rot13, and Daniel Kahneman
14 points9 comments
Ygeorgehill ·
GPT-4 is coming next week – and it will be multimodal, says Microsoft Germany
8 points2 comments
Ygtsnexp ·
Ask HN: What dataset was used to train ChatGPT? How can we find out?
3 points1 comments
Yjosefslerka ·
Training language models to follow instructions with human feedback [pdf]
3 points0 comments
Ytosh ·
Training language models to follow instructions with human feedback
2 points0 comments
Ynadermx ·
The paper that made ChatGPT possible
2 points0 comments
Ypps ·
Open Assistant – project meant to give everyone access to a great chat based LLM
2 points1 comments
Y7moritz7 ·
I made ChatGPT and Bing AI have a conversation
2 points1 comments
Yscraptor ·
Lawyer cites fake cases invented by ChatGPT, judge is not amused
2 points0 comments
YGarcia98 ·
Chain-of-Thought Hub: Measuring LLMs' Reasoning Performance
2 points0 comments
Ynatolambert ·
How RLHF Works
2 points0 comments
Ygnicholas ·
A New Chat Bot Is a ‘Code Red’ for Google’s Search Business
1 points0 comments
Ysillysaurusx ·
Show HN: Llama-dl – high-speed download of LLaMA, Facebook's 65B GPT model
1 points0 comments
Ygeorgehill ·
Microsoft lays off an ethical AI team as it doubles down on OpenAI
1 points0 comments
Ytosh ·
Training language models to follow instructions with human feedback
1 points0 comments
Yhighfrequency ·
Has ChatGPT Been Neutered?
1 points0 comments
Yspdustin ·
All of ChatGPT's System Prompts
1 points0 comments
Yandrehacker ·
What was your "Oh Shit" moment with GenAI?
1 points1 comments