AI & machine learning2022 · shared on Hacker News
Large Language Models are Zero-Shot Reasoners: Let's think step by step
Explore Large Language Models are Zero-Shot Reasoners: Let's think step by step, 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.
Ymeetpateltech ·
Magistral — the first reasoning model by Mistral AI
941 points424 comments
Ynmwnmw ·
Llama 3.2: Revolutionizing edge AI and vision with open, customizable models
924 points328 comments
Yeatonphil ·
LaMDA is not sentient
366 points662 comments
YAnon84 ·
Large models of what? Mistaking engineering achievements for linguistic agency
184 points156 comments
Ysandebert ·
ChatGPT can't kill anything worth preserving
68 points77 comments
YGrowtika ·
LLMs are a 400-year-long confidence trick
11 points2 comments
Yhellovai ·
What we learned from using GPT for 500k+ classifications
9 points1 comments
Yszopa ·
Teaching ChatGPT to Speak My Son’s Invented Language
5 points0 comments
YHammadB ·
Large Language Models are Zero-Shot Reasoners: Let's think step by step
4 points0 comments
Yseanherron ·
Tech’s hottest new job: AI whisperer. No coding required
3 points0 comments
YColinEberhardt ·
Re-implementing LangChain in 100 lines of code
3 points0 comments
Yjellyberg ·
Compare how GPT-2, 3, 3.5 and 4 answer the same questions
3 points0 comments
YNM_Ricky ·
ChatGPT Cheat Sheet
2 points2 comments
Yandyk ·
Show HN: Recursive LLM Prompts
2 points2 comments
Yog_kalu ·
Think Before You Speak: Training Language Models with Pause Tokens
2 points0 comments
Yarchon1410 ·
Large Language Models Are Zero-Shot Reasoners
1 points0 comments
Yatleastoptimal ·
GPT-4 performs significantly worse on coding problems not in its training data
1 points0 comments