AI & machine learning2022 · shared on Hacker News
Training Compute-Optimal Large Language Models
Explore Training Compute-Optimal Large Language Models, 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 #48560093 Comment #46324366 Comment #44808589 Comment #43937317 Comment #38677460 Comment #38662687 Comment #37937668 Comment #37550394 Comment #36883432 Comment #36777492 Comment #36700825 Comment #35810294 Comment #35810215 Comment #35737571 Comment #35631428 Comment #35577425 Comment #35508682 Comment #35332959 Comment #35299718 Comment #35110454 Comment #34944775 Comment #34936903 Comment #34861412 Comment #34751882 Comment #34682566 Comment #34146825 Comment #34049644 Comment #34028941 Comment #33730551 Comment #33342468 Comment #32945083 Comment #32527518 Comment #32462472 Comment #30995935 Comment #30982442 Comment #30981024 Comment #30914697 Comment #30912871
Yhardmaru ·
Stable Diffusion 2.0
1,320 points471 comments
Yiamwil ·
History LLMs: Models trained exclusively on pre-1913 texts
876 points410 comments
Yjasondavies ·
John Carmack's new AGI company, Keen Technologies, has raised a $20M round
461 points619 comments
Yhomarp ·
Pathways Language Model (PaLM): Scaling to 540B parameters
235 points207 comments
Yfriggeri ·
Llama 2 – Meta AI
235 points55 comments
Ygeorgehill ·
DeepMind’s New Language Model, Chinchilla
229 points142 comments
YHard_Space ·
The road to realistic full-body deepfakes
220 points201 comments
Yraldi ·
GPT-3 can create both sides of an Interactive Fiction transcript
132 points68 comments
Yjmsflknr ·
Sundar Pichai: An important next step on our AI journey
127 points78 comments
YBostonian ·
Why do LLMs have emergent properties?
83 points110 comments
Ydavidbarker ·
Stability AI Launches the First of Its StableLM Suite of Language Models
76 points15 comments
Ygardenfelder ·
The LLama Effect: Leak Sparked a Series of Open Source Alternatives to ChatGPT
58 points7 comments
YBrajeshwar ·
Estimating PaLM's Training Cost
51 points17 comments
Yerwald ·
The Prospect of an AI Winter
44 points17 comments
Ytosh ·
SparseGPT: Language Models Can Be Accurately Pruned in One-Shot
24 points1 comments
Ygslin ·
Stability AI releases its latest image-generating model, Stable Diffusion XL 1.0
24 points7 comments
Yviburnum ·
Carmack Leaves Meta
21 points2 comments
Youtrun86 ·
Consortium launched to build the largest open LLM
18 points5 comments
Yog_kalu ·
Large Language Models for Compiler Optimization
15 points1 comments
Ymfiguiere ·
LLaMA: A foundational, 65B-parameter large language model
12 points6 comments
Yqualudeheart ·
Training Compute-Optimal Large Language Models
8 points0 comments
Yfaustog ·
70B language model outperforms Gopher and GPT-3
5 points0 comments
Yadityaathalye ·
The wall confronting large language models
5 points1 comments
Ymonort ·
Language Models Can Teach Themselves to Program Better
4 points1 comments
Ymetalwhale ·
Open source solution replicates ChatGPT training process
4 points0 comments
YDDSDev ·
OpenAI’s CEO confirms the company isn’t training GPT-5 and ‘won’t for some time’
4 points3 comments
Yvsroy ·
Llama 1.3B Trained on 200B Tokens for Commercial Use
4 points1 comments
Yhmokiguess ·
Cohere's First Model for Developers
4 points0 comments
Yzuhayeer ·
Training Compute-Optimal Large Language Models
3 points0 comments
Ysquidhunter ·
GPT in 60 Lines of NumPy
3 points0 comments
Yswyx ·
Replit's new Code LLM: Open Source, 77% smaller than Codex, trained in 1 week
3 points0 comments
Ysharonzhou ·
Free and Fast LLM Finetuning
3 points3 comments
Yjjwiseman ·
Copilot Internals
2 points0 comments
Ymrtksn ·
LLaMA-7B in Pure C++ with full Apple Silicon support
2 points1 comments
Ybelter ·
Do large language models need all those layers?
2 points0 comments
Ygmays ·
Training Compute-Optimal Large Language Models
1 points0 comments
Ykrm01 ·
Ask HN: What's the value ratio of GPT3's LLM vs. its training data?
1 points2 comments
Yatleastoptimal ·
GPT-4 performs significantly worse on coding problems not in its training data
1 points0 comments
Yhahnchen ·
Ask HN: AI/ML papers to catch up with current state of AI?
1 points0 comments