Hacker Papers
- 226
UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
Hacker News threads
- Jan 2019UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- Aug 2018A visualization of the prime factors of the first million integers
- Aug 2018A visualization of the prime factors of the first million integers
- Dec 2018Let’s Try t-SNE
- Jan 2019Structure of recent philosophy (2017)
- Feb 2019Topological methods for unsupervised learning problems [video]
- Apr 2019Applied Category Theory
- Oct 2024Category Theory Illustrated: Logic (2021)
- 227
The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
Hacker News threads
- Oct 2023The Geometry of Truth: Emergent Linear Structure in How LLMs Represent Truth
- Oct 2023"Hallucinating" AIs Sound Creative, but Let's Not Celebrate Being Wrong
- Nov 2023Ask HN: What is your standard for judging when AGI exists?
- Nov 2023Rats have an imagination, new research suggests
- Nov 2023HN thread 38355930
- May 2024Google scrambles to manually remove weird AI answers in search
- Sep 2024AI is growing faster than companies can secure it, warn industry leaders
- Sep 2024GPTs and Hallucination
- Aug 2025Persona vectors: Monitoring and controlling character traits in language models
- 228
On the Paradox of Learning to Reason from Data
Hacker News threads
- Aug 2022On the Paradox of Learning to Reason from Data
- Jun 2024The Paradox of Learning to Reason from Data (2022)
- Jul 2023On the Paradox of Learning to Reason from Data
- Dec 2022Artificial Intelligence Is Stupid and Causal Reasoning Will Not Fix It
- Feb 2023Getty Images v. Stability AI – Complaint
- Mar 2023Understanding ChatGPT
- Mar 2023HN thread 35320870
- Jul 2023PoisonGPT: We hid a lobotomized LLM on Hugging Face to spread fake news
- Sep 2023Provably safe systems: the only path to controllable AGI
- Oct 2024DeepSeek: Advancing theorem proving in LLMs through large-scale synthetic data
- 229
Universal Language Model Fine-tuning for Text Classification
Hacker News threads
- Mar 2025The algo that advanced natural language processing and influenced OpenAI's LLMs
- Jan 2018Language Models for Classification (state of art on everything)
- Jan 2018Fine-Tuned Language Models for Text Classification [pdf]
- Feb 2018Learning Word Vectors for 157 Languages
- May 2018State-of-the-art text classification with universal language models
- May 2018Our machine learning and NLP journey
- Jun 2018Improving Language Understanding with Unsupervised Learning
- Jul 2018NLP's ImageNet Moment: From Shallow to Deep Pre-Training
- Jul 2020Classifying 200k articles in 7 hours using NLP
- Nov 2023OpenAI Announces Leadership Transition
- 230
End-to-End Training of Deep Visuomotor Policies
Hacker News threads
- Jul 2015End-To-End Training of Deep Visuomotor Policies
- May 2015End-to-End Training of Deep Visuomotor Policies [pdf]
- May 2015‘Deep learning’ technique enables robot mastery of skills via trial and error
- May 2015‘Deep learning’ technique enables robot mastery of skills via trial and error
- Oct 2015Obstacles on the Path to AI
- Oct 2015Obstacles on the Path to AI
- Dec 2015The first person to hack the iPhone is building a self-driving car
- Apr 2016An AI First World
- May 2016My path to OpenAI
- May 2017AlphaGo beats Ke Jie again to wrap up three-part match
- 231
Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models
Hacker News threads
- Aug 2024A Study on the Impact of Structured Output on Performance of LLMs
- Aug 2024A Study on the Impact of Format Restrictions on Performance of LLM
- Aug 2024A Study on the Impact of Format Restrictions on Performance of LLMs
- Aug 2024Structured Outputs in the API
- Sep 2024Show HN: Best Practices for Using Structured Output from LLMs
- Sep 2025Sampling and structured outputs in LLMs
- Jul 2026How to stop Claude from saying load-bearing
- Aug 2026Why does Opus 5 feel worse to work with?
- Oct 2026Fixing Tool-Call Accuracy in vLLM
- 232
Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
Hacker News threads
- Feb 2015Towards AI-Complete Question Answering, Using Deep Learning
- Feb 2015Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks [pdf]
- Mar 2015Facebook's Memory Networks Demo
- Mar 2015By 2029 no computer or “machine intelligence” will have passed the Turing Test
- Jun 2015Hound voice search NLP demo [video]
- Aug 2015Towards Neural Network-based Reasoning
- Sep 2015Inferring Algorithmic Patterns with Stack
- Jun 2016DeepText: Facebook's text understanding engine
- Oct 2025A History of Large Language Models
- 233
STaR: Bootstrapping Reasoning With Reasoning
Hacker News threads
- 234
Relating transformers to models and neural representations of the hippocampal formation
Hacker News threads
- Apr 2022Relating Transformers to Modes and Neural Representations of the Hippocampal
- May 2022Relating transformers to neural representations of hippocampal formation
- Apr 2022Relating Transformers to Neural Representations of the Hippocampal Formation
- Apr 2022Playing with DALL-E 2
- Dec 2022Ask HN: How to get back into AI?
- Jan 2024Understand how transformers work by demystifying the math behind them
- Jun 2024A most profound video game: a good cognitive aid for research
- Sep 2024Kolmogorov-Arnold networks may make neural networks more understandable
- Nov 2025The Case That A.I. Is Thinking
- 235
Text Embeddings Reveal (Almost) As Much As Text
Hacker News threads
- Oct 2023Text Embeddings Reveal (Almost) as Much as Text
- Nov 2023Show HN: Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context
- Dec 2023Embeddings, Vectors, and Arithmetic
- Mar 2024Launch HN: Greptile (YC W24) - RAG on codebases that actually works
- Jun 2024CryptGPT: A Simple Approach to Privacy-Preserving LLMs Using Vigenere Cipher
- Jul 2024Vision language models are blind
- Jan 2025Let's talk about AI and end-to-end encryption
- 236
Refusal in Language Models Is Mediated by a Single Direction
Hacker News threads
- Jun 2024Refusal in language models is mediated by a single direction
- May 2026Refusal in Language Models Is Mediated by a Single Direction
- Jul 2024Explainability is not a game
- Nov 2025Heretic: Automatic censorship removal for language models
- Nov 2025Heretic: Automatic censorship removal for language models
- Jul 2026OpenAI and Hugging Face partner to address security incident
- Sep 2026US Military had close call after using AI for hallucinated intelligence report
- Sep 2026Pirate Face Rescues LLM Models from Deletion
- Sep 2026Pirate Face Rescues LLM Models from Deletion
- Oct 2026IBM CEO says open weight models are now good and cheap on-prem
- 237
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Hacker News threads
- Feb 2017Photo-Realistic Single Image Super-Resolution Using a Adversarial Network
- Sep 2016Photo-Realistic Single Image Super-Resolution
- Oct 2016Subpixel: A subpixel convolutional neural network implementation with Tensorflow
- Oct 2016Subpixel: A subpixel convolutional neural network implementation with Tensorflow
- Oct 2016Neural Enhance – Super Resolution for images using deep learning
- Oct 2016Neural Enhance – Super Resolution for images using deep learning
- Nov 2016RAISR Sharp Images with Machine Learning
- Dec 2016Major advancements in Deep Learning in 2016
- Jan 2017With Google's RAISR, images can be up to 75% smaller without losing detail
- Jul 2020Ask HN: What weird or hard problems are you trying to solve?
- 238
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Hacker News threads
- Jun 2019XLNet: Generalized Autoregressive Pretraining for Language Understanding
- Jun 2019The transformer “explained”?
- Jul 2019MT-DNN Achieves Human Performance in General Language Understanding Benchmark
- Aug 2019GPT-2: 6-Month Follow-Up
- Aug 2019Natural Language Processing: The Age of Transformers
- Aug 2020Deep learning job postings have collapsed in the past six months
- May 2022Show HN: Catchy melodies made with a diffusion-based neural net assistant
- May 2022Teaching GPT-3 to reverse words
- 239
Giraffe: Using Deep Reinforcement Learning to Play Chess
Hacker News threads
- Sep 2015Giraffe: Using Deep Reinforcement Learning to Play Chess
- Sep 2015Giraffe: Using Deep Reinforcement Learning to Play Chess
- Sep 2015Giraffe: Using Deep Reinforcement Learning to Play Chess
- Sep 2015Deep Learning Machine Teaches Itself International Master Level Chess in 72 HRs
- Sep 2015In just 72 hours a deep learning engine has learned chess to Master level
- Mar 2016Spawkfish: Neural network chess
- Oct 2017AlphaGo Zero: Learning from scratch
- Nov 2017Alpha Go Zero: How and Why It Works
- Nov 2017AI Uses Less Than Two Minutes of Videogame Footage to Recreate Game Engine
- Dec 2017Mastering Chess and Shogi by Self-Play with General Reinforcement Learning
- 240
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
- 241
Deep Differentiable Logic Gate Networks
Hacker News threads
- Feb 2023Logic Gate Simulator
- Dec 2023Transformers on Chips
- Sep 2024GSoC'24: Differentiable Logic for Interactive Systems and Generative Music
- May 2025Compiling a neural net to C for a speedup
- May 2025Compiling a neural net to C for a speedup
- Nov 2025Weight-sparse transformers have interpretable circuits [pdf]
- Nov 2025TPUs vs. GPUs and why Google is positioned to win AI race in the long term
- 242
Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
Hacker News threads
- Nov 2016Zero shot translation learning
- Nov 2016Multilingual Neural Machine Translation
- Feb 2017Google's Zero-Shot Multilingual Neural Machine Translation System
- Nov 2016Peeking into the architecture used for Google's Neural Machine Translation
- Jan 2017Why Deep Learning Cannot Be Applied to Natural Languages Easily
- Jan 2017Why Deep Learning Cannot Be Applied to Natural Languages Easily
- Jan 2017Why Deep Learning Cannot Be Applied to Natural Languages Easily
- Mar 2017Basque and Georgian – are they related? (2015)
- Jul 2017Researchers shut down AI that invented its own language
- Feb 2018The Shallowness of Google Translate
- 243
Self-Instruct: Aligning Language Models with Self-Generated Instructions
Hacker News threads
- Apr 2023Self-Instruct: Aligning Language Model with Self Generated Instructions
- Mar 2023The genie escapes: Stanford copies the ChatGPT AI for less than $600
- Mar 2023Show HN: Finetune LLaMA-7B on commodity GPUs using your own text
- May 2023LIMA: Less Is More for Alignment
- Dec 2023Ask HN: AI/ML papers to catch up with current state of AI?
- Dec 2024The Curse of Recursion: Training on generated data makes models forget (2023)
- Jan 2025AI Engineer Reading List
- 244
Deduplicating Training Data Makes Language Models Better
Hacker News threads
- May 2022Google fires another AI researcher who reportedly challenged findings
- Aug 2022Chinchilla's Wild Implications
- Aug 2022Exploring 12M of the 2.3B images used to train Stable Diffusion
- Nov 2022Ask HN: What can I personally do to fight AGAINST the Copilot class action?
- Jun 2024Large language model data pipelines and Common Crawl
- Jan 202530% drop in O1-preview accuracy when Putnam problems are slightly variated
- 245
Alignment faking in large language models
Hacker News threads
- Dec 2024AIs Will Increasingly Fake Alignment
- Feb 2025Efficient Reasoning with Hidden Thinking
- Feb 2025Scaling up test-time compute with latent reasoning: A recurrent depth approach
- Aug 2025Is chain-of-thought AI reasoning a mirage?
- Feb 2026An AI Agent Published a Hit Piece on Me – The Operator Came Forward
- Mar 2026Sarvam 105B, the first competitive Indian open source LLM
- 246
RWKV: Reinventing RNNs for the Transformer Era
Hacker News threads
- May 2023RWKV: Reinventing RNNs for the Transformer Era
- Jul 2023Scaling Transformers to 1B Tokens
- Nov 2023Is anyone using self hosted LLM day to day and training it like a new employee
- Dec 2023Paving the way to efficient architectures: StripedHyena-7B
- Jan 2024Eagle 7B: Soaring past Transformers
- Jan 2024Eagle 7B: Soaring past Transformers
- Feb 2025Ask HN: Is anybody building an alternative transformer?
- 247
Self-Consuming Generative Models Go MAD
Hacker News threads
- Jan 2024Self-Consuming Generative Models Go MAD
- Aug 2023Self-Consuming Generative Models Go Mad
- Jul 2023AI Loses Its Mind After Being Trained on AI-Generated Data
- Jul 2023AI Loses Its Mind After Being Trained on AI-Generated Data
- Oct 2023Why Generative AI Is Currently Doomed
- Apr 2024Google Books Is Indexing AI-Generated Garbage
- Jul 2024AI models collapse when trained on recursively generated data
- Sep 2026Nvidia wants to put a watchdog chip next to every AI agent
- 248
Universal Transformers
Hacker News threads
- Nov 2018A Google Brain engineer’s guide to entering AI
- Sep 2019Attention Mechanism in Deep Learning
- Aug 2025The Drivers of HRM's Performance on Arc-AGI
- Oct 2025Less is more: Recursive reasoning with tiny networks
- Oct 2025Less is more: Recursive reasoning with tiny networks
- Dec 2025Universal Reasoning Model (53.8% pass 1 ARC1 and 16.0% ARC 2)
- 249
Generative Language Modeling for Automated Theorem Proving
Hacker News threads
- Sep 2020Generative Language Modeling for Automated Theorem Proving
- Sep 2020Generative Language Modeling for Automated Theorem Proving
- Sep 2020Graph Representations for Higher-Order Logic and Theorem Proving (2019)
- Sep 2020At the International Mathematical Olympiad, computers prepare to go for the gold
- Sep 2020The Collatz Conjecture: the simple math problem we still can’t solve
- Nov 2020AI Expert Roadmap
- Jan 2021DALL·E: Creating Images from Text
- Jun 2021Mathematicians welcome computer-assisted proof in ‘grand unification’ theory
- Jul 2024AI solves International Math Olympiad problems at silver medal level
- 250
Predictive Coding Approximates Backprop along Arbitrary Computation Graphs
Hacker News threads
- May 2021Predictive Coding Approximates Backprop Along Arbitrary Computation Graphs (2020)
- Feb 2021Artificial Neural Nets Finally Yield Clues to How Brains Learn
- Apr 2021Predictive coding has been unified with backpropagation
- Apr 2021Cerebras’ new monster AI chip adds 1.4T transistors
- Apr 2021The Fourier transform is a neural network
- Jun 2023Artificial brains help understand real brains
- Sep 2023What Is an Emotion? William James’s Theory of How Our Bodies Affect Our Feelings
- May 2024Energy, not compute, will be the #1 bottleneck to AI progress – Mark Zuckerberg [video]
Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.