Hacker Papers
- 01
Deep Residual Learning for Image Recognition
Hacker News threads
- Dec 2015Deep Residual Learning for Image Recognition
- Dec 2015Deep Residual Learning for Image Recognition
- Dec 2015Microsoft Research wins image recognition competition
- Mar 2016Leaf: Machine learning framework in Rust
- Jun 2016What is the difference between deep learning and usual machine learning?
- Jun 2018Ask HN: Can you recommend any ML papers or blogs for visual art detection?
- Aug 2020China hires over 100 TSMC engineers in push for chip leadership
- Apr 2021Predictive coding has been unified with backpropagation
- Nov 2023Simplifying Transformer Blocks
- Oct 2026We're releasing the weights of Mistral Large 4
- 02
Concrete Problems in AI Safety
Hacker News threads
- Jun 2016Concrete Problems in AI Safety
- Jun 2016Concrete Problems in AI Safety
- Nov 2017AI Safety: problem of accidents in machine learning systems
- Jun 2016Concrete AI Safety Problems
- May 2017The world’s biggest problems and why they’re not what first comes to mind
- Oct 2017OpenAI's Researchers: Protecting Against AI’s Existential Threat
- Oct 2018Ask HN: Examples of AI ethical principles?
- Nov 2019Safety Gym
- May 2021Anthropic AI
- Apr 2023Yann LeCun and Andrew Ng: Why the 6-Month AI Pause Is a Bad Idea [video]
- Jul 2026Our position on open-weights models
- 03
CycleGAN, a Master of Steganography
Hacker News threads
- Jan 2019CycleGAN, a Master of Steganography [2017]
- Jan 2019CycleGAN, a Master of Steganography
- Sep 2024Minifying HTML for GPT-4o: Remove all the HTML tags
- Aug 2025How attention sinks keep language models stable
- Mar 2026No right to relicense this project
- Oct 2026Write Like It's 1866: LLMs Relearn Telegraphese
- 04
On Calibration of Modern Neural Networks
Hacker News threads
- Apr 2018Tesla issues strongest statement yet blaming driver for deadly crash
- Apr 2021Smart Folk Often Full of Crap, Study Finds
- Jan 2023Overconfidence and AI
- Sep 2023Can LLMs learn from a single example?
- Sep 2026Jev in 25 Lines of Python
- Oct 2026Decision models like Jev don't beat LLM-as-a-judge or traditional classifiers
- 05
Attention Is All You Need
Hacker News threads
- Jun 2017Deep Neural Networks – Attention is all you need (No recurrence or convolutions)
- Jun 2017Attention Is All You Need (Neural Networks)
- Jun 2025Attention Is All You Need
- Jun 2017Exploring LSTMs
- Apr 2020Building an end-to-end Speech Recognition model in PyTorch
- Mar 2023Google internally developed chatbots like ChatGPT years ago
- May 2023Why the Original Transformer LLM Figure Is Wrong, and Other Interesting Tidbits
- Dec 2023Ask HN: Daily practices for building AI/ML skills?
- Jan 2025Tensor Product Attention Is All You Need
- Mar 2026Ask HN: What are the greatest discoveries in the last few years?
- Sep 2026The AI Race Just Got Awkward
- 06
On the Measure of Intelligence
Hacker News threads
- Nov 2019The Measure of Intelligence: towards more human-like artificial systems
- Jun 2024The Measure of Intelligence
- Nov 2019François Chollet: The Measure of Intelligence
- Nov 2019What Would the Father of Cybernetics Think About A.I. Today?
- Jul 2020OpenAI's GPT-3 may be the biggest thing since Bitcoin
- Dec 2020Ask HN: What's the best paper you've read in 2020?
- Jan 2023What Is AGI-Hard
- Mar 2024AIs ranked by IQ; AI passes 100 IQ for first time, with release of Claude-3
- Oct 2024Ask HN: Who is hiring? (October 2024)
- Jul 2025François Chollet: The Arc Prize and How We Get to AGI [video]
- Sep 2026Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
- 07
Deep reinforcement learning from human preferences
Hacker News threads
- Feb 2018Deep reinforcement learning from human preferences
- Jul 2018Evolving Floorplans
- Mar 2019Ask HN: Game devs, what is the hardest part about designing an AI for your game?
- Oct 2019The problem with metrics is a big problem for AI
- Mar 2023Microsoft lays off an ethical AI team as it doubles down on OpenAI
- Aug 2025Curious about the training data of OpenAI's new GPT-OSS models? I was too
- Sep 2026We must pace the frontier
- 08
Fine-Tuning Language Models from Human Preferences
Hacker News threads
- Dec 2019Controlling Text Generation with Plug and Play Language Models
- Mar 2023Microsoft lays off an ethical AI team as it doubles down on OpenAI
- Sep 2023
- Apr 2024When Will the GenAI Bubble Burst?
- Jan 2025OpenAI says it has evidence DeepSeek used its model to train competitor
- Aug 2025Anthropic's CEO says in 3-6 months, AI will write 90% of the code (March 2025)
- Sep 2026I resigned from Anthropic today
- 09
Distilling the Knowledge in a Neural Network
Hacker News threads
- Mar 2015Distilling the Knowledge in a Neural Network
- Jul 2015How Google Translate squeezes deep learning onto a phone
- Mar 2016AlphaGo beats Lee Sedol 3-0 [video]
- Apr 2017The Myth of a Superhuman AI
- Dec 2017Neural Networks in JavaScript with Deeplearn.js
- Apr 2022Scientists discover specific neurons involved in making memories
- Mar 2023Could you train a ChatGPT-beating model for $85,000 and run it in a browser?
- Mar 2026NanoGPT Slowrun: 10x Data Efficiency with Infinite Compute
- Aug 2026OpenAI: GPT 5.6 Sol price reduction (until at least Nov 21)
- 10
Logical Induction
Hacker News threads
- 11
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
Hacker News threads
- Jan 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-Of-Experts Layer
- Jun 2019Outrageously Large Neural Nets: Sparsely-Gated Mixture-of-Experts Layer (2017)
- Jan 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-Of-Experts Layer
- Jul 2017Show HN: Xcessiv – Fully managed web application for automated machine learning
- Apr 2018Skynet Today – accessible and informed coverage of AI hype and panic
- Nov 2019Deep Learning and Its Implications for Computer Architecture and Chip Design
- Jul 2023FTC investigating ChatGPT over potential consumer harm
- Dec 2023Mistral "Mixtral" 8x7B 32k model [magnet]
- Dec 2023Visualizing expert firing frequencies in Mixtral MoE
- Jun 2024AI Search: The Bitter-Er Lesson
- Jul 2026Kimi-K3 Technical Report [pdf]
- 12
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Hacker News threads
- Nov 2015Unsupervised Rep. Learning with Deep Convolutional Generative Advers. Nets
- Jul 2026Unsupervised Representation Learning with Deep Convolutional GANs
- Dec 2015Ask HN: Papers you read in 2015?
- Mar 2016Yann LeCun's comment on AlphaGo and true AI
- Mar 2016Tensorflow Implementation of Deep Visual Analogy-Making
- Apr 2016Technologists have produced a 3D-printed painting in the style of Rembrandt
- Jun 2016Blade Runner re-encoded using neural networks
- Jun 2016Generative Models
- Jul 2017When not to use deep learning
- 13
Are Transformers universal approximators of sequence-to-sequence functions?
Hacker News threads
- May 2023Ask HN: Why can GPT4 en/decode base64?
- Mar 2024OpenAI – transformer debugger release
- Nov 2025The Case That A.I. Is Thinking
- Feb 2026The Problem with LLMs
- Jun 2026ChatGPT Spontaneously Generates Sexual Violence and Hardcore Snuff Imagery
- Jun 2026ChatGPT Spontaneously Generates Sexual Violence and Hardcore Snuff Imagery
- 14
Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
Hacker News threads
- 15
Magic: The Gathering is Turing Complete
Hacker News threads
- May 2019Magic: The Gathering is Turing Complete
- Dec 2023Magic: The Gathering Is Turing Complete (2019)
- Feb 2022Magic: The Gathering is Turing Complete (2019)
- Aug 2019Rediscovering rules for ancient board games
- Jun 2020How the Magic: The Gathering Color Wheel Explains Humanity
- Jun 2022AI Is Ushering in a New Scientific Revolution
- Dec 2022“Magic: The Gathering” is officially the world’s most complex game
- Jul 2023Show HN: Marsha – An LLM-Based Programming Language
- Dec 2023I Hacked Magic the Gathering: Arena for a 100% Win Rate
- Sep 2024Deal infinite damage for 4GRU, as long as the twin primes conjecture is true
- Jun 2026MTG Bench: Testing how well LLMs can play magic
- 16
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]
- 17
A Neural Conversational Model
Hacker News threads
- Jun 2015A Neural Conversational Model [pdf]
- Jun 2015A Neural Conversational Model [pdf]
- Jul 2015Getting closer to 'Ex Machina' – A Neural Conversational Model by Google[pdf]
- Jun 2015Artificial Intelligence Machine Gets Testy with Its Programmer
- Aug 2015A Beginner’s Guide to Restricted Boltzmann Machines
- Jan 2016BotLibre – Free Open Artificial Intelligence for Everyone
- Mar 2016Generating Factoid Questions with RNNs: The 30M Factoid Question-Answer Corpus
- Jun 2016The truth about deep learning
- Nov 2016Show HN: Spamnesty: Waste spammers' time
- Jan 2020Towards a conversational agent that can chat about anything
- Jun 2026What was your "Oh Shit" moment with GenAI?
- 18
The Case for Learned Index Structures
Hacker News threads
- Dec 2017The Case for Learned Index Structures
- Dec 2017The Case for Learned Index Structures
- Dec 2017The Case for Learned Index Structures
- Dec 2017Machine Learning for Systems and Systems for Machine Learning [pdf]
- Dec 2017My Favorite Papers of 2017
- Feb 2018Chip advances require fresh ideas, speakers say
- May 2018An O(N) Sorting Algorithm: Machine Learning Sorting
- Nov 2018Optimal Shard Placement in a Petabyte Scale Elasticsearch Cluster
- Oct 2020Using Lidar to Add Autofocus to a Manual Focus Lens
- Jul 2022Ask HN: What are some cool but obscure data structures you know about?
- Jun 2026"They're made out of weights"
- 19
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Hacker News threads
- Oct 2018BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding
- Apr 2023Bert: Pre-Training of Deep Bidirectional Transformers for Language Understanding
- Nov 2018TensorFlow Code for Google Research's BERT: Pre-Training Method for NLP Tasks
- Feb 2019Microsoft’s New MT-DNN Outperforms Google BERT
- Mar 2019Yann LeCun, Geoffrey Hinton and Yoshua Bengio win Turing Award
- Sep 2019At Tech’s Leading Edge, Worry About a Concentration of Power
- Mar 2023Google internally developed chatbots like ChatGPT years ago
- Jul 2023Ask HN: How to Break into AI Engineering
- Oct 2023Ask HN: Why is OpenAI still called OpenAI?
- Jun 2026Superintelligence: The Idea That Eats Smart People (2016)
- 20
Deep Double Descent: Where Bigger Models and More Data Hurt
Hacker News threads
- Dec 2019Deep Double Descent: Where Bigger Models and More Data Hurt
- Dec 2019Understanding “Deep Double Descent”
- Jul 2020The Overfitted Brain: Dreams evolved to assist generalization
- Oct 2021Imitating Deep Learning Dynamics via Stochastic Differential Equations
- Apr 2023Double Descent in Human Learning
- May 2023What are some of the best written papers in AI,ML,DL and its applications?
- Feb 2026I don't think AGI is imminent
- May 2026Making Deep Learning Go Brrrr from First Principles
- 21
Polynomial Regression As an Alternative to Neural Nets
Hacker News threads
- Jun 2018Polynomial Regression as an Alternative to Neural Nets
- Jun 2018Polynomial Regression as an Alternative to Neural Nets
- Sep 2019NNs are in fact essentially polynomial regression models
- Aug 2019Neural Networks Are Essentially Polynomial Regression
- Aug 2020Differentiable Control Problems
- Oct 2020Why deep learning works even though it shouldn’t
- May 2021Complexity is a source of income in open source ecosystems (2019)
- May 2026A polynomial autoencoder beats PCA on transformer embeddings
- 22
KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning
Hacker News threads
- 23
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Hacker News threads
- Jul 2018The Lottery Ticket Hypothesis: Finding Small, Trainable Neural Networks
- Mar 2018The Lottery Ticket Hypothesis: Training Pruned Neural Networks
- Oct 2020The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks (2019)
- May 2019Smarter Training of Neural Networks
- Aug 2019Exploring Weight Agnostic Neural Networks
- Jun 2020Neurons that fire together, wire together, but how?
- Jul 2021Mammals dream about the world they are about to experience before they are born
- Oct 2022Substitute certain overhyped programming terms with more accurate replacements
- May 2023AI intensifies fight against ‘paper mills’ that churn out fake research
- Jan 2025OpenAI says it has evidence DeepSeek used its model to train competitor
- Apr 2026Show HN: SparseLab–real sparse training(CSR+custom kernel) in PyTorch, CPU-first
- 24
Neural Machine Translation of Rare Words with Subword Units
Hacker News threads
- 25
An Introduction to Probabilistic Programming
Hacker News threads
- Oct 2018An Introduction to Probabilistic Programming
- Oct 2021An Introduction to Probabilistic Programming
- Mar 2026An Introduction to Probabilistic Programming (2018)
- Oct 2018Google DeepMind Founder Demis Hassabis: Three Truths about AI
- Nov 2018Karl Friston: a neuroscientist who might hold the key to true AI
- Jun 2019A general-purpose probabilistic programming system with programmable inference
- Dec 2020Foundations of Probabilistic Programming
- Mar 2022Probabilistic Models of Cognition
- Aug 2023A History of Clojure (2020) [pdf]
Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.