人工智能2020 · 分享于 Hacker News
Scaling Laws for Neural Language Models
探索《Scaling Laws for Neural Language Models》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 #48822131 评论 #48822006 评论 #48610405 评论 #48164363 评论 #47259998 评论 #46999857 评论 #44842355 评论 #43265315 评论 #42843543 评论 #42026219 评论 #41809830 评论 #41662144 评论 #41659199 评论 #40398434 评论 #39661476 评论 #39213942 评论 #39056442 评论 #38660341 评论 #37145964 评论 #36879837 评论 #36035458 评论 #35577425 评论 #35229842 评论 #34990580 评论 #34935301 评论 #34797791 帖子正文 #34686313 评论 #34557589 评论 #30911170 评论 #30735729 评论 #28838745 评论 #28217528 评论 #26230794 评论 #25825959 评论 #25823486 评论 #24372611 评论 #24372139 评论 #22147970
Yjspann ·
OpenAI to become for-profit company
1,346 赞同745 评论
Ysieste ·
GPT-Neo – Building a GPT-3-sized model, open source and free
725 赞同252 评论
Yeigenvalue ·
The impact of competition and DeepSeek on Nvidia
655 赞同479 评论
Ysh_tomer ·
Ilya Sutskever: “If you learn all of these, you’ll know 90% of what matters”
313 赞同110 评论
Yhnhn34 ·
Understanding the Limitations of Mathematical Reasoning in LLMs
282 赞同266 评论
Yhomarp ·
Pathways Language Model (PaLM): Scaling to 540B parameters
235 赞同207 评论
YTenoke ·
Talking to myself: how I trained GPT2-1.5b for rubber ducking using my chat data
217 赞同67 评论
Ymfiguiere ·
Mark Zuckerberg’s new goal is creating artificial general intelligence
209 赞同338 评论
Ysebg ·
Learning@home hivemind – train large neural networks across the internet
148 赞同38 评论
Ydbrereton ·
Bing AI Can't Be Trusted
142 赞同58 评论
Ygsky ·
OpenAI in throes of executive exodus as three walk at once
137 赞同128 评论
Ytmfi ·
Complexity No Bar to AI
120 赞同118 评论
Yselimonder ·
Megatron-Turing NLG 530B, the World’s Largest Generative Language Model
116 赞同99 评论
Ynsoonhui ·
It’s Like GPT-3 but for Code – Fun, Fast, and Full of Flaws
91 赞同68 评论
Ynpmipg ·
GPU-rich labs have won: What's left for the rest of us is distillation
88 赞同50 评论
Yfzliu ·
Matryoshka Representation Learning
83 赞同11 评论
Yebalit ·
AMD Open-Source 1B OLMo Language Models
78 赞同33 评论
Ylnyan ·
Program Synthesis with Large Language Models
63 赞同20 评论
Yminimaxir ·
Introducing ChatGPT and Whisper APIs
53 赞同17 评论
Yupmind ·
Ask HN: How worried are you about being replaced by an LLM
18 赞同47 评论
Yksec ·
Intel Announces Aurora GenAI, ChatGPT Competitor with 1T Parameters
15 赞同0 评论
Ymfiguiere ·
LLaMA: A foundational, 65B-parameter large language model
12 赞同6 评论
Ykiyanwang ·
"It's a lemon"–OpenAI's largest AI model ever arrives to mixed reviews
5 赞同4 评论
YDDSDev ·
OpenAI’s CEO confirms the company isn’t training GPT-5 and ‘won’t for some time’
4 赞同3 评论
Ybirriel ·
How Is LLaMa.cpp Possible?
4 赞同0 评论
Yatg_abhishek ·
Scaling Laws for Neural Language Models
3 赞同0 评论
Yjnord ·
Jensen Huang says Nvidia is pulling back from OpenAI and Anthropic
3 赞同0 评论
Yoshrimpton ·
GPT-5.5 hallucinates 3x more than MIT-licensed GLM-5.2
3 赞同0 评论
YLordNibbler ·
Scaling Laws for Neural Language Models
2 赞同0 评论
Ydoener ·
Newer data once again shows: the human brain is just a scaled up primate brain
2 赞同0 评论
Ysnow_mac ·
Which GPU(s) to Get for Deep Learning
2 赞同1 评论
Ybelter ·
Do large language models need all those layers?
2 赞同0 评论
Yashvardanian ·
Transcending Scaling Laws with 0.1% Extra Compute
1 赞同0 评论
Yffwd ·
Ask HN: How “real” are AI scaling laws?
1 赞同1 评论
Yvinhnx ·
The Problem with LLMs
1 赞同0 评论
Yelsewhen ·
US Is Starting to See Heavy Job Losses in Roles Exposed to AI
1 赞同0 评论
Ynotmcrowley ·
30papers.com – Ilya's 30 essential ML papers, in a beginner friendly format
1 赞同0 评论