思想与社会2023 · 分享于 Hacker News
Transformers struggle with generalizing tasks beyond pre-training data
探索《Transformers struggle with generalizing tasks beyond pre-training data》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。
Ymfiguiere ·
OpenAI and Elon Musk
1,037 赞同977 评论
Ytodsacerdoti ·
Markov chains are funnier than LLMs
525 赞同233 评论
Yspwestwood ·
Seven replies to the viral Apple reasoning paper and why they fall short
343 赞同312 评论
Ysaliagato ·
Will scaling work?
242 赞同283 评论
Yhomarp ·
Chess-GPT's Internal World Model
120 赞同103 评论
Yryandvm ·
New theory suggests LLMs can understand text
79 赞同106 评论
Ydmotz ·
Gemini – Google DeepMind
59 赞同11 评论
Yhislaziness ·
Transformers struggle with generalizing tasks beyond pre-training data
36 赞同36 评论
Yagomez314 ·
Evidence that transformers cannot generalize beyond their training data
3 赞同0 评论
Ygardenfelder ·
Google researchers deal a major blow to the theory AI about to outsmart humans
2 赞同1 评论
Yistotex ·
AI is about to change how you use computers
2 赞同1 评论
YYeGoblynQueenne ·
Pretraining Data Mixtures Enable Narrow Model Selection Capabil. In Transformers
1 赞同0 评论
Yvagabund ·
Weak-to-Strong Generalization
1 赞同0 评论