Hacker Papers
- 26
A Neural Algorithm of Artistic Style
Hacker News threads
- Aug 2015A Neural Algorithm of Artistic Style [pdf]
- Aug 2015A Neural Algorithm of Artistic Style [pdf]
- Aug 2015A Neural Algorithm of Artistic Style
- Aug 2015
- Sep 2015Algorithm can create new Van Gogh or Picasso in an hour
- Feb 2016Visual Turing Test
- Apr 2016Technologists have produced a 3D-printed painting in the style of Rembrandt
- Sep 2016Implementation of Neural Style Transfer in Python and Keras
- Mar 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Nov 2017Confession as an AI researcher; seeking advice
- Apr 2023Study: ChatGPT Outperforms Physicians in Quality, Empathetic Answers to Patients
- 27
The Pile: An 800GB Dataset of Diverse Text for Language Modeling
Hacker News threads
- Jun 2023The Pile: An 800GB Dataset of Diverse Text for Language Modeling
- May 2021The Pile: An 800GB Dataset of Diverse Text for Language Modeling
- Jul 2023The Pile: a dataset for language modeling [pdf]
- Mar 2021The makers of Eleuther hope it will be an open source alternative to GPT-3
- Apr 2022Textsynth: Bellard's free GPT-NeoX-20B, GPT-J playground and paid API
- Jan 2023The Limits of GPT-3 and Similar Large Language Models
- Apr 2023RedPajama: Reproduction of Llama with Friendly License (Stanford, MILA Quebec)
- Jul 2023Sarah Silverman is suing OpenAI and Meta for copyright infringement
- Sep 2023What OpenAI Really Wants
- Mar 2024DBRX: A new open LLM
- Apr 2026Even 'uncensored' models can't say what they want
- 28
The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Hacker News threads
- Apr 2018When algorithms surprise us
- Mar 2018Surprising Creativity: Anecdotes from Evolutionary Computation
- Mar 2018The Surprising Creativity of Digital Evolution: Artifical Life and EC Anecdotes
- Mar 2018Evolution Is the New Deep Learning
- Jun 2018Can “effective altruism” maximise the bang for each charitable buck?
- Nov 2018Evolved antenna
- Apr 2019Notes on AI Bias
- Mar 2021Lying to the Ghost in the Machine
- Jun 2021One bee has cloned itself millions of times over the past three decades
- Aug 2022John Carmack's new AGI company, Keen Technologies, has raised a $20M round
- Jun 2023Own-Goal Football (2022)
- 29
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Hacker News threads
- Apr 2022An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Jul 2021Deep reinforcement learning is a waste of time (2019)
- Mar 2022Transformers, originally designed to handle language, are taking on vision
- Mar 2023The Most Cited AI Papers in 2022
- Jun 2023What Is a Transformer Model?
- Feb 2024The killer app of Gemini Pro 1.5 is using video as an input
- Oct 2024Show HN: Doctly AI – Accurate AI-Powered PDF to Markdown Parser
- Jul 2025Baba Is Eval
- Sep 2026Ask HN: (Why) Was the LLM breakthrough useful for images, audio, etc.?
- 30
Learning in High Dimension Always Amounts to Extrapolation
Hacker News threads
- Oct 2023Learning in High Dimension Always Amounts to Extrapolation
- Nov 2023Learning in High Dimension Always Amounts to Extrapolation
- Dec 2021Training computer vision models on random noise instead of real images
- May 2022The Scaling Hypothesis (2021)
- Oct 2023The copyright fight over authors and OpenAI's ChatGPT
- Nov 2023Transformers struggle with generalizing tasks beyond pre-training data
- Mar 2024Large language models can do jaw-dropping things. But nobody knows why
- Oct 2024GitHub cuts AI deals with Google, Anthropic
- Feb 2026GPT-5.2 derives a new result in theoretical physics
- Oct 2026“Math 2.0” will need to value mathematical progress more holistically
- 31
In-Datacenter Performance Analysis of a Tensor Processing Unit
Hacker News threads
- Dec 2017In-Datacenter Performance Analysis of a Tensor Processing Unit
- May 2017Dave Patterson: Evaluation of the Tensor Processing Unit
- Jun 2017The Age of Nvidia
- Aug 2017Google TPU Performance Analysis
- Feb 2018Cloud TPUs in Beta
- Apr 2019Tesla Live Stream – Autonomy Day [video]
- Feb 2023Introduction to FPGAs
- Oct 2024Video Surveillance with YOLO+llava
- Apr 2025Google is winning on every AI front
- 32
DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning
Hacker News threads
- Dec 2023DreamCoder: Growing Generalizable, Interpretable Knowledge
- Jun 2020DreamCoder: Growing generalizable, interpretable knowledge with program learning
- Feb 2021DreamCoder, a system that learns to solve problems by writing programs
- Dec 2020Ask HN: What's the best paper you've read in 2020?
- May 2021Kobra – visual programming language for machine learning
- Nov 2021GPT-3 is no longer the only game in town
- Feb 2022Competitive Programming with AlphaCode
- Feb 2022Competitive Programming with AlphaCode
- Jul 2022AI Coding with CodeRL: Toward Mastering Program Synthesis with Deep RL
- Sep 2023Doug Lenat has died
- May 2026Language Models Need Sleep
- 33
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Hacker News threads
- Sep 2016“Why Should I Trust You?” Explaining the Predictions of Any Classifier [pdf]
- Apr 2016[pdf] Explaining the Predictions of Any Classifier
- Oct 2020Explaining black box models with LIME
- Sep 2016Explainable Artificial Intelligence (XAI) Darpa Funding
- Mar 2017War by any means: The story of DARPA
- Jul 2017Thoughts on OpenAI, reinforcement learning, and killer robots
- Dec 2017DeepVariant: Highly Accurate Genomes with Deep Neural Networks
- Dec 2017A friend of mine died and I didn't know because of algorithms
- Jul 2019Interpretable Machine Learning
- Apr 2020Introduction to Support Vector Machines in Machine Learning
- Jun 2024No physics? No problem. AI weather forecasting is already making strides
- 34
Model Cards for Model Reporting
Hacker News threads
- Jul 2020Yann LeCun quits Twitter amid acrimonious exchanges on AI bias
- Jul 2020Yann LeCun quits Twitter amid acrimonious exchanges on AI bias
- Aug 2023AI Nutrition Facts
- Dec 2023Will scaling work?
- Dec 2024OpenAI o1 system card
- Jul 2025ChatGPT agent System Card [pdf]
- May 2026Grok 4.3
- Jun 2026System Card: Claude Fable 5 and Claude Mythos 5 [pdf]
- 35
One weird trick for parallelizing convolutional neural networks
Hacker News threads
- Jul 2014One weird trick for parallelizing convolutional neural networks
- Apr 2014Data Scientist Interviews
- Aug 2014ImageNet Large Scale Visual Recognition Competition
- Nov 2015TensorFlow: open-source library for machine intelligence
- Dec 2015Ask HN: Papers you read in 2015?
- May 2016NVIDIA Announces the GeForce GTX 1000 Series
- Jul 2016Nvidia CEO Reveals New TITAN X at Stanford Deep Learning Meetup
- Feb 2020Microsoft Zero and DeepSpeed: Memory Efficient Large Neural Network Training
- Jun 2022Techniques for Training Large Neural Networks
- 36
World Models
Hacker News threads
- Jun 2018World Models
- Mar 2018World Models
- Apr 2018A step-by-step guide to the “World Models” AI paper
- Jul 2018Ask HN: 2018 Summer Reading List?
- Nov 2019The revolution of machine learning has been exaggerated
- Jun 2021DeepMind says reinforcement learning is ‘enough’ to reach general AI
- Jul 2021More Protein Folding Progress – What’s It Mean?
- Sep 2025'World Models,' an old idea in AI, mount a comeback
- Feb 2026The Waymo World Model: A New Frontier for Autonomous Driving Simulation
- 37
Thinking Like Transformers
Hacker News threads
- Jun 2021Thinking Like Transformers
- Jun 2023Thinking Like Transformers (pdf)
- Dec 2021The potential of transformers in reinforcement learning
- May 2023It's not just statistics: GPT-4 does reason
- Jun 2023From Word Models to World Models
- Aug 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Models
- Sep 2023I made a transformer by hand (no training)
- Apr 2024Mixture-of-Depths: Dynamically allocating compute in transformers
- Nov 2025Ask HN: How are Markov chains so different from tiny LLMs?
- Feb 2026I want to wash my car. The car wash is 50 meters away. Should I walk or drive?
- 38
WaveNet: A Generative Model for Raw Audio
Hacker News threads
- Nov 2016Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition
- Mar 2017Baidu Deep Voice Explained: Part 1 – the Inference Pipeline
- Oct 2017Finding Waldo Using Semantic Segmentation and Tiramisu
- May 2018Today’s dominant approach to A.I. has not worked out
- Oct 2018A Tour of the Top Algorithms for Machine Learning Newbies
- Apr 2019Ask HN: What is the state of the art in text to speech?
- Aug 2022Show HN: Nevermind XOR – Deep Learning Has an Issue with Sin
- Jan 2026Pocket TTS: A high quality TTS that gives your CPU a voice
- 39
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
Hacker News threads
- Feb 2015Ask HN: How do you find important/interesting new papers
- Dec 2015Machine learning works spectacularly well, but mathematicians aren’t sure why
- Jan 2016New finding: 600M years ago, a single mutation changed everything
- Oct 2017The quest to evolve neural networks through evolutionary algorithms
- Mar 2019Backpropogation Is Just Steepest Descent with Automatic Differentiation (2013)
- Mar 2019Backpropogation Is Just Steepest Descent with Automatic Differentiation (2013)
- Oct 2020Why deep learning works even though it shouldn’t
- Jun 2026Puzzling Success of Overparameterization: Lottery Tickets or Escape Dimensions?
- 40
Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes
Hacker News threads
- Jan 2017Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity,
- Aug 2019Driven by Compression Progress (Schmidhuber, 2008)
- Apr 2023Driven By Compression Progress (2008)
- Sep 2017Ask HN: CS as a philosophy
- Oct 2017Intelligence Reconsidered
- Mar 2021Information Is Surprise (2015)
- Mar 2021Hutter Prize
- Jul 2024Creativity fundamentally comes from memorization?
- Mar 2025ARC-AGI without pretraining
- Aug 2026Compression Is Prediction
- Sep 2026Asking Authors About Their Own Papers
- 41
Hopfield Networks is All You Need
Hacker News threads
- Aug 2025Hopfield Networks Is All You Need (2020)
- Aug 2020Hopfield Networks Is All You Need
- Aug 2020Hopfield Networks Is All You Need
- Aug 2021Introduction to Convolutional Neural Networks
- Feb 2022Ask HN: Is GitHub Copilot / IntelliCode Legal?
- Sep 2022Transformers seem to mimic parts of the brain
- Jul 2023Retentive Network: A Successor to Transformer for Large Language Models
- Jul 2023Retentive Network: A Successor to Transformer for Large Language Models
- Mar 2024Short-term Hebbian learning can implement transformer-like attention
- Feb 2025LM2: Large Memory Models
- Jan 2026The Q, K, V Matrices
- 42
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Hacker News threads
- Apr 2022Chain of Thought Prompting Elicits Reasoning in Large Language Models
- Dec 2022Chain of Thought Prompting Elicits Reasoning in Large Language Models
- Apr 2022Pathways Language Model (PaLM): Scaling to 540B parameters
- Jul 2022Am I doing it wrong? (OpenAI test)
- Mar 2023Oceania Always at War with Eastasia: Generative AI and Knowledge Pollution
- Apr 2023Teaching ChatGPT to Speak My Son’s Invented Language
- Aug 2023GPT-4 Can't Reason
- Sep 2024Training Language Models to Self-Correct via Reinforcement Learning
- Oct 2025Ortega hypothesis
- Sep 2026GPT-6 Astra
- 43
Emergent Abilities of Large Language Models
Hacker News threads
- Feb 2023Emergent Abilities of Large Language Models
- May 2024Emergent Abilities of Large Language Models
- Apr 2023Emergent Abilities of Large Language Models
- Dec 2022Ask HN: How does ChatGPT work?
- Feb 2023It Looks Like You’re Trying to Take over the World
- May 2023LLMs are not greater than the sum of their parts: Stanford researchers
- Jul 2023Llama 2 – Meta AI
- Nov 2023Telling GPT-4 you're scared or under pressure improves performance
- Mar 2024“Emergent” abilities in LLMs actually develop gradually and predictably – study
- Feb 2025Understanding Reasoning LLMs
- Aug 2026Humanity has the debate about AI consciousness backwards
- 44
Evaluating Large Language Models Trained on Code
Hacker News threads
- Jul 2021Evaluating Large Language Models Trained on Code
- Jul 2021Evaluating Large Language Models Trained on Code
- Jul 2021Evaluating Large Language Models Trained on Code (paper about GH copilot model)
- Jul 2021All public GitHub code was used in training Copilot
- Sep 2021GitHub Copilot Generated Insecure Code in 40% of Circumstances During Experiment
- Dec 2021GPT-3 APIs are now in public beta
- Jul 2022ML code generation vs. coding by hand: what we think programming will look like
- May 2023Replit's new Code LLM: Open Source, 77% smaller than Codex, trained in 1 week
- Oct 2023Show HN: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context
- Feb 2025AI is stifling new tech adoption?
- Jul 2025Mercury: Ultra-fast language models based on diffusion
- 45
Training language models to follow instructions with human feedback
Hacker News threads
- Jan 2023Training language models to follow instructions with human feedback [pdf]
- Dec 2022Training language models to follow instructions with human feedback
- Apr 2023Training language models to follow instructions with human feedback
- Oct 2022GPT-3 can create both sides of an Interactive Fiction transcript
- Jan 2023Announcement: AI generated answers are officially banned here
- Feb 2023What Is ChatGPT Doing and Why Does It Work?
- Mar 2023Microsoft lays off an ethical AI team as it doubles down on OpenAI
- May 2023Lawyer cites fake cases invented by ChatGPT, judge is not amused
- Jun 2023How RLHF Works
- Jun 2024Safe Superintelligence Inc.
- Sep 2026I built non-autoregressive decision models with RL a year ago
- 46
Large Language Models are Zero-Shot Reasoners
Hacker News threads
- May 2022Large Language Models are Zero-Shot Reasoners: Let's think step by step
- May 2022Large Language Models Are Zero-Shot Reasoners
- Jun 2022LaMDA is not sentient
- Feb 2023Tech’s hottest new job: AI whisperer. No coding required
- Apr 2023Teaching ChatGPT to Speak My Son’s Invented Language
- Jul 2023What we learned from using GPT for 500k+ classifications
- Oct 2023Think Before You Speak: Training Language Models with Pause Tokens
- Jul 2024Large models of what? Mistaking engineering achievements for linguistic agency
- Mar 2025ChatGPT can't kill anything worth preserving
- Jan 2026LLMs are a 400-year-long confidence trick
- 47
Playing Atari with Deep Reinforcement Learning
Hacker News threads
- Oct 2014Playing Atari with Deep Reinforcement Learning [pdf]
- Jan 2015Playing Atari with Deep Reinforcement Learning (2013) [pdf]
- Jan 2014Deep Mind's neural networks play 7 Atari 2600 games with more skill than a human
- Jan 2014Google to Buy Artificial Intelligence Startup DeepMind for $400M
- Jan 2014Applying Artificial Intelligence to Nintendo Tetris
- Dec 2014Google's Intelligence Designer
- Jan 2015Mario Lives: An AI for creating a living and conversing agent [video]
- Feb 2015Human-level control through deep reinforcement learning
- May 2016End to End Learning for Self-Driving Cars [pdf]
- Jan 2017CS 294 Deep Reinforcement Learning, Spring 2017
- Jan 2024Self-Rewarding Language Models
- 48
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Hacker News threads
- Dec 2014Deep Neural Networks Are Easily Fooled
- Dec 2014Deep Neural Networks Are Easily Fooled [pdf]
- Dec 2014Deep Learning Reading List
- Jun 2015Facial recognition technology is everywhere, and it may not be legal
- Nov 2015Impressive Demonstration of Facebook's AI by Yann LeCun
- May 2016IBM is not doing "cognitive computing" with Watson
- Jun 2016AI, Deep Learning, and Machine Learning: A Primer [video]
- Oct 2016Google AI invents its own cryptographic algorithm
- Jul 2017NO Need to Worry about Adversarial Examples for Autonomous Vehicles
- Jun 2019Why is Stack Overflow trying to start audio?
- 49
Learning to learn by gradient descent by gradient descent
Hacker News threads
- Jun 2016Learning to learn by gradient descent by gradient descent
- Jun 2016Learning to learn by gradient descent by gradient descent
- Jun 2016Learning to learn by gradient descent by gradient descent
- Aug 2016News Feed FYI: Further Reducing Clickbait in Feed
- Dec 2016Tool AIs want to be agent AIs
- Jan 2017Darpa Goes “Meta” with Machine Learning for Machine Learning (2016)
- Jan 2017Darpa Goes “Meta” with Machine Learning for Machine Learning (2016)
- Feb 2017The Convex Geometry of Inverse Problems [video]
- Jul 2017Hacker's guide to Neural Networks (2012)
- Oct 2019Gradient Descent: The Ultimate Optimizer
- Mar 2025Optimizing ML training with metagradient descent
- 50
On the Turing Completeness of Modern Neural Network Architectures
Hacker News threads
- May 2019On the Turing Completeness of Modern NN Architectures (Transformer, Neural GPU)
- Jul 2020Is This a Turing Machine?
- Sep 2020Graph Representations for Higher-Order Logic and Theorem Proving (2019)
- Sep 2022Ladybird: A new cross-platform browser project
- Jan 2023Petals: Run 100B+ language models at home bit-torrent style
- Mar 2023GPT-4
- Apr 2023There Is No A.I
- Sep 2024Tinygrad will be the next Linux and LLVM
- Feb 2025Efficient Reasoning with Hidden Thinking
Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.