AI & machine learning2022 · shared on Hacker News
Discovering Latent Knowledge in Language Models Without Supervision
Explore Discovering Latent Knowledge in Language Models Without Supervision, 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.
Yoccamschainsaw ·
GPT o3 frequently fabricates actions, then elaborately justifies these actions
75 points72 comments
Ycratermoon ·
ChatGPT Isn't 'Hallucinating'–It's Bullshitting – Scientific American
62 points25 comments
Ysaeedesmaili ·
AI is making it easier to create more noise, when all I want is good search
58 points8 comments
YMurizS ·
AlphaCode Attention Visualization
23 points7 comments
YBuhljingo ·
Generative AI is overrated, long live old-school AI
23 points0 comments
Ydayve ·
Discovering Latent Knowledge in Language Models Without Supervision
12 points0 comments
Yjmsflknr ·
Microsoft Adds ChatGPT AI Technology to Bing Search Engine
7 points0 comments
Yfreyfogle ·
ChatGPT is falsely recommending us for a service we don't provide
4 points1 comments
Ymfiguiere ·
ChatGPT get-rich-quick schemes are coming for magazines, Amazon, and YouTube
2 points0 comments
Ysimonebrunozzi ·
Discovering Latent Knowledge in Language Models Without Supervision
1 points0 comments
Ymaraoz ·
ChatRWKV, like ChatGPT but powered by the RWKV (RNN-based, open) language model
1 points0 comments
Yexcerionsforte ·
ArxivGPT: Chrome extension that summarizes arxived research papers using ChatGPT
1 points0 comments