Will We Run Out of Data? Limits of LLM Scaling Based on Human-Generated Data (epochai.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of epochai.org: Will We Run Out of Data? Limits of LLM Scaling Based on Human-Generated Data

First screen, captured 2 years ago.

Looks similar

Screenshot of epochai.org: Will we run out of ML data? Evidence from projecting dataset size trends (2022)

Will we run out of ML data? Evidence from projecting dataset size trends (2022)(epochai.org)

53 points by kurhan 3 years ago | 93 comments

Screenshot of dylancastillo.co: Honey, I shrunk the embeddings: Matryoshka vs. PCA

Honey, I shrunk the embeddings: Matryoshka vs. PCA (dylancastillo.co)

60 points by dcastm 2 months ago | 12 comments

Screenshot of allenai.github.io: Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs

Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs (allenai.github.io)

82 points by milliondreams 2 years ago | 7 comments

Screenshot of epochai.org: Notable AI Models

Notable AI Models (epochai.org)

7 points by cheptsov 2 years ago | 0 comments

Screenshot of baseten.co: Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs

Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs (baseten.co)

215 points by philipkiely 1 year ago | 142 comments

Screenshot of qlabs.sh: NanoGPT Slowrun: Language Modeling with Limited Data, Infinite Compute

NanoGPT Slowrun: Language Modeling with Limited Data, Infinite Compute (qlabs.sh)

173 points by sdpmas 7 months ago | 31 comments