Hacker News Reader

www1.ece.neu.edu3 ptspanabee

0

mRNA-LM: full-length integrated SLM for mRNA analysis

academic.oup.com4 ptspanabee

0

DiLoCo: Distributed Low-Communication Training of Language Models

huggingface.co3 ptspanabee

0

Revised Chinchilla scaling laws – LLM compute and token requirements

educatingsilicon.com1 ptspanabee

0

Compute-Optimal Context Size

manifestai.com3 ptspanabee

0

An Empirical Study of Mamba-Based Language Models

arxiv.org43 ptspanabee

3

Human Language Understanding and Reasoning (2022)

amacad.org1 ptspanabee

0

MapReduce: A Flexible Data Processing Tool (2010)

cacm.acm.org3 ptspanabee

1

RLHF: Reinforcement Learning from Human Feedback

huyenchip.com1 ptspanabee

0

Gemini 1.5 Model Family: Technical Report [pdf]

storage.googleapis.com57 ptspanabee

3

Illuminate: Turn academic papers into AI-generated audio discussions

illuminate.withgoogle.com3 ptspanabee

1

Sparse Llama: 70% Smaller, 3x Faster, Full Accuracy

cerebras.net40 ptspanabee

1

Mitochondria and Chloroplasts

khanacademy.org2 ptspanabee

0

Asian American women are getting lung cancer despite never smoking

nbcnews.com148 ptspanabee

146

CatLIP: Clip Vision Accuracy with 2.7x Faster Pre-Training on Web-Scale Data

arxiv.org48 ptspanabee

4

Patchscopes: A framework for viewing hidden representations of language models

research.google12 ptspanabee

0

Understanding Diffusion Models: A Unified Perspective

arxiv.org2 ptspanabee

0

Fast-forward – comparing a 1980s supercomputer to the modern smartphone

blog.adobe.com2 ptspanabee

0

Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient LMs

arxiv.org1 ptspanabee

0

Prostate cancer includes two different evotypes

ox.ac.uk152 ptspanabee

84

Stanford researchers: 45% of GPT4 responses to medical queries hallucinate

twitter.com3 ptspanabee

4

Understanding Diffusion Models: A Unified Perspective

ar5iv.labs.arxiv.org3 ptspanabee

0

The promises and pitfalls of specialized ribosomes (2022)

sciencedirect.com2 ptspanabee

0

Shallow Feed-Forward Neural Networks as Alternative to Attention in Transformers

huggingface.co11 ptspanabee

0

New Bing attracts new Edge users – who then use Google Search

searchengineland.com2 ptspanabee

0

FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores

hazyresearch.stanford.edu3 ptspanabee

0

The core contribution of "Attention is All You Need" is logistic regressions

twitter.com1 ptspanabee

1

'Anti-hunger' molecule forms after exercise, scientists discover (2022)

med.stanford.edu1 ptspanabee

0

LeanDojo: Theorem Proving with Retrieval-Augmented Language Models

leandojo.org1 ptspanabee

0

panabee

Ask HN: When human experts disagree, how should machines determine truth?

Creative Thinking by Claude Shannon

mRNA-LM: full-length integrated SLM for mRNA analysis

DiLoCo: Distributed Low-Communication Training of Language Models

Revised Chinchilla scaling laws – LLM compute and token requirements

Compute-Optimal Context Size

An Empirical Study of Mamba-Based Language Models

Human Language Understanding and Reasoning (2022)

MapReduce: A Flexible Data Processing Tool (2010)

RLHF: Reinforcement Learning from Human Feedback

Gemini 1.5 Model Family: Technical Report [pdf]

Illuminate: Turn academic papers into AI-generated audio discussions

Sparse Llama: 70% Smaller, 3x Faster, Full Accuracy

Mitochondria and Chloroplasts

Asian American women are getting lung cancer despite never smoking

CatLIP: Clip Vision Accuracy with 2.7x Faster Pre-Training on Web-Scale Data

Patchscopes: A framework for viewing hidden representations of language models

Understanding Diffusion Models: A Unified Perspective

Fast-forward – comparing a 1980s supercomputer to the modern smartphone

Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient LMs

Prostate cancer includes two different evotypes

Stanford researchers: 45% of GPT4 responses to medical queries hallucinate

Understanding Diffusion Models: A Unified Perspective

The promises and pitfalls of specialized ribosomes (2022)

Shallow Feed-Forward Neural Networks as Alternative to Attention in Transformers

New Bing attracts new Edge users – who then use Google Search

FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores

The core contribution of "Attention is All You Need" is logistic regressions

'Anti-hunger' molecule forms after exercise, scientists discover (2022)

LeanDojo: Theorem Proving with Retrieval-Augmented Language Models