Hacker News headlines

2

A History of Nvidia Stream Multiprocessor (2020) (fabiensanglard.net)

4 months ago | jxmorris12 | fabiensanglard.net | newest

3

Gaming TruthfulQA: Simple Heuristics Exposed Dataset Weaknesses (turntrout.com)

4 months ago | jxmorris12 | turntrout.com | newest

1

Ε, a Nuisance No More (zna.do)

4 months ago | jxmorris12 | zna.do | frontpage

1

Learning CUDA by Optimizing Softmax (maharshi.bearblog.dev)

4 months ago | jxmorris12 | bearblog.dev | newest

1

History of Residuals and a Word of Caution (lucasb.eyer.be)

4 months ago | jxmorris12 | eyer.be | newest

1

MixBox: Practical Pigment Mixing for Digital Painting [pdf] (scrtwpns.com)

4 months ago | jxmorris12 | scrtwpns.com | newest

2

Detecting Tanks (2017) (jefftk.com)

4 months ago | jxmorris12 | jefftk.com | newest

1

The Bittersweet Lesson (docs.google.com)

4 months ago | jxmorris12 | google.com | newest

2

Why transformers are obviously good models of language (arxiv.org)

4 months ago | jxmorris12 | arxiv.org | newest

2

What would happen if you made a planet out of fish? (james-simon.github.io)

5 months ago | jxmorris12 | github.io | frontpage

1

Diffusion Meets Flow Matching: Two Sides of the Same Coin (diffusionflow.github.io)

5 months ago | jxmorris12 | github.io | newest

1

Educating Silicon (educatingsilicon.com)

5 months ago | jxmorris12 | educatingsilicon.com | newest

2

Quick software tips for new ML researchers (eugenevinitsky.com)

5 months ago | jxmorris12 | eugenevinitsky.com | newest

2

The Baked Data architectural pattern (simonwillison.net)

5 months ago | jxmorris12 | simonwillison.net | newest

1

What Is Entropix Doing? (timkellogg.me)

5 months ago | jxmorris12 | timkellogg.me | newest

1

DeltaNet Explained (Part I) (sustcsonglin.github.io)

5 months ago | jxmorris12 | github.io | newest

1

How To Change Your Behavior (might.net)

5 months ago | jxmorris12 | might.net | newest

1

Infini-Gram: Scaling Unbounded N-Gram Language Models to a Trillion Tokens (infini-gram.io)

5 months ago | jxmorris12 | infini-gram.io | newest

1

Making Transformers Do Math (vatsadev.github.io)

5 months ago | jxmorris12 | github.io | newest

1

Sunsethue – Today's Sunset Forecast (sunsethue.com)

6 months ago | jxmorris12 | sunsethue.com | newest

1

An Unserious Take on Axiomatic Knowledge in the Era of Foundation Models (stanford.edu)

6 months ago | jxmorris12 | stanford.edu | newest

2

A Meticulous Guide to Advances in Deep Learning Efficiency over the Years (alexzhang13.github.io)

7 months ago | jxmorris12 | github.io | newest

1

Clowning in Pennsylvania (sjmielke.com)

7 months ago | jxmorris12 | sjmielke.com | newest

1

Contextual Document Embeddings (arxiv.org)

7 months ago | jxmorris12 | arxiv.org | newest

1

Experiments in Self-Assembly (james-simon.github.io)

9 months ago | jxmorris12 | github.io | newest

1

Matrixmultiplication.xyz (matrixmultiplication.xyz)

10 months ago | jxmorris12 | matrixmultiplication.xyz | newest

1

Not Quite Past – Real Ceramic Tiles Designed by AI (notquitepast.com)

10 months ago | jxmorris12 | notquitepast.com | newest

1

Data Compression with Arithmetic Coding (marknelson.us)

11 months ago | jxmorris12 | marknelson.us | newest

1

Int4 Decoding GQA CUDA Optimizations for LLM Inference (pytorch.org)

11 months ago | jxmorris12 | pytorch.org | newest

2

Einsum Is Easy and Useful (ejenner.com)

11 months ago | jxmorris12 | ejenner.com | newest

1

Optimizing Matrix Multiplication (coffeebeforearch.github.io)

11 months ago | jxmorris12 | github.io | newest

1

Kullback-Leibler (KL) Is All You Need (alexalemi.com)

12 months ago | jxmorris12 | alexalemi.com | newest

2

How Do Language Models Put Attention Weights over Long Context? (yaofu.notion.site)

12 months ago | jxmorris12 | notion.site | newest

3

Chess Engines: A Zero to One (super.site)

12 months ago | jxmorris12 | super.site | newest

1

A Personal History of Legion, by Way of Its Papers (elliottslaughter.com)

12 months ago | jxmorris12 | elliottslaughter.com | newest

2

Bananagrams Is NP-Complete (joshengels.com)

12 months ago | jxmorris12 | joshengels.com | newest

1

A Better Lesson (rodneybrooks.com)

a year ago | jxmorris12 | rodneybrooks.com | newest

1

Seeking the Productive Life: Some Details of My Personal Infrastructure (stephenwolfram.com)

a year ago | jxmorris12 | stephenwolfram.com | newest

2

A Neighborhood with Friends (tynan.com)

a year ago | jxmorris12 | tynan.com | newest

102

How to graduate your PhD when you have no hope (huiwenn.github.io)

a year ago | jxmorris12 | github.io | best

1

PyTorch Word Embeddings Tutorial (pytorch.org)

a year ago | jxmorris12 | pytorch.org | newest

28

Integer Tokenization Is Insane (2023) (beren.io)

a year ago | jxmorris12 | beren.io | frontpage

90

Diffusion models from scratch, from a new theoretical perspective (chenyang.co)

a year ago | jxmorris12 | chenyang.co | best

1

A Refined Similarity-Based Bigram Model (demoriarty.github.io)

a year ago | jxmorris12 | github.io | newest

1

Speculative Sampling (jaykmody.com)

a year ago | jxmorris12 | jaykmody.com | newest

2

An Introduction to Optimization: Combinatorial Optimization (dougfenstermacher.com)

a year ago | jxmorris12 | dougfenstermacher.com | newest

2

Definite Optimism as Human Capital (danwang.co)

a year ago | jxmorris12 | danwang.co | newest

0

Singular Value Decomposition Part 1: Perspectives on Linear Algebra (jeremykun.com)

a year ago | jxmorris12 | jeremykun.com | newest

0

Singular Value Decomposition as Simply as Possible (gregorygundersen.com)

a year ago | jxmorris12 | gregorygundersen.com | newest

2

Too much efficiency makes everything worse: overfitting and Goodhart's law (sohl-dickstein.github.io)

a year ago | jxmorris12 | github.io | newest

1

Detecting Mismatches in Machine-Learning Systems (cmu.edu)

a year ago | jxmorris12 | cmu.edu | newest

3

Meta-Learning: Learning to Learn Fast (lilianweng.github.io)

a year ago | jxmorris12 | github.io | newest

1

Diagnosing and Debugging PyTorch Data Starvation (willprice.dev)

a year ago | jxmorris12 | willprice.dev | newest

2

Delving into what happens when you `import torch` (pytorch.org)

a year ago | jxmorris12 | pytorch.org | newest

4

I don't like the word "Just" (todepond.com)

a year ago | jxmorris12 | todepond.com | newest

3

Guidance: A cheat code for diffusion models (sander.ai)

a year ago | jxmorris12 | sander.ai | newest

1

Weeks of Your Life (weeksofyour.life)

a year ago | jxmorris12 | weeksofyour.life | newest

1

Speculative Decoding (philkrav.com)

a year ago | jxmorris12 | philkrav.com | newest

1

An Engineer's Guide to GEMM (petewarden.com)

a year ago | jxmorris12 | petewarden.com | newest

2

A Python Implementation of Simhash Algorithm (leons.im)

a year ago | jxmorris12 | leons.im | newest

89

Why is machine learning 'hard'? (2016) (stanford.edu)

a year ago | jxmorris12 | stanford.edu | best

129

Machine Learning Is Still Too Hard for Software Engineers (nyckel.com)

a year ago | jxmorris12 | nyckel.com | best

6

Meta-Learning Is All You Need (2020) (jameskle.com)

a year ago | jxmorris12 | jameskle.com | frontpage

1

The Three Types of Contrastive Learning (jxmo.io)

a year ago | jxmorris12 | jxmo.io | newest

23

Inverting PhotoDNA (2021) (anishathalye.com)

a year ago | jxmorris12 | anishathalye.com | best

2

Programming and Writing (antirez.com)

a year ago | jxmorris12 | antirez.com | newest

2

Evolution as Backstop for Reinforcement Learning (gwern.net)

a year ago | jxmorris12 | gwern.net | newest

1

Self-Serving Utilitarian Arguments (askell.blog)

a year ago | jxmorris12 | askell.blog | newest

1

Building AGI Using Language Models (2020) (bmk.sh)

a year ago | jxmorris12 | bmk.sh | newest

2

A Short Introduction to Optimal Transport and Wasserstein Distance (alexhwilliams.info)

a year ago | jxmorris12 | alexhwilliams.info | newest

2

WildChat offering free access to GPT-4 turbo for a limited time (twitter.com/wzhao_nlp)

a year ago | jxmorris12 | twitter.com | newest

1

Training open-source LLMs is a losing battle, a complete dead end (twitter.com/jxmnop)

a year ago | jxmorris12 | twitter.com | newest

48

Echo Chess: The Quest for Solvability (samiramly.com)

a year ago | jxmorris12 | samiramly.com | best

26

Text Embeddings Reveal (Almost) as Much as Text (openreview.net)

a year ago | jxmorris12 | openreview.net | best

1

SimCLR in PyTorch – An ELI5 Guide (zablo.net)

2 years ago | jxmorris12 | zablo.net | newest