Hacker Papers
- 451
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
Hacker News threads
- May 2023SparseGPT: Language Models Can Be Accurately Pruned in One-Shot
- Jan 2023Some Remarks on Large Language Models – Yoav Goldberg
- Mar 2023Neural Chip Plays Doom Using a Thousandth of a Watt
- Apr 2023Stability AI Launches the First of Its StableLM Suite of Language Models
- Apr 2023GitHub Copilot emits GPL code
- May 2023How to run Llama 13B with a 6GB graphics card
- May 2023OpenAI chief goes before US Congress to propose licenses for building AI
- Apr 2024Show HN: Speeding up LLM inference 2x times (possibly)
- 452
Large Language Diffusion Models
Hacker News threads
- Feb 2025Large Language Diffusion Models
- Feb 2025Large Language Diffusion Models
- Feb 2025Diffusion LLM Has Arrived
- Feb 2025I think Yann Lecun was right about LLMs (but perhaps only by accident)
- Feb 2025I think Yann Lecun was right about LLMs (but perhaps only by accident)
- Mar 2025Beyond Diffusion: Inductive Moment Matching
- Mar 2025Ask HN: Any insider takes on Yann LeCun's push against current architectures?
- Apr 2025Yann LeCun, Pioneer of AI, Thinks Today's LLM's Are Nearly Obsolete
- May 2025Mercury: Commercial-scale diffusion language model
- Feb 2026Consistency diffusion language models: Up to 14x faster, no quality loss
- 453
Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
Hacker News threads
- Jun 2025Give Me FP32 or Give Me Death?
- Sep 2026Understanding, Mitigating Numerical Sources of Nondeterminism in LLM Inference
- Jun 2025TPU Deep Dive
- Jul 2025LLMs as Compilers
- Jul 2025Grok: Searching X for "From:Elonmusk (Israel or Palestine or Hamas or Gaza)"
- Feb 2026LLMs could be, but shouldn't be compilers
- Mar 2026Surpassing vLLM with a Generated Inference Stack
- Aug 2026What my dad taught me about AI coding in the 90s
- 454
Deep Learning with Limited Numerical Precision
Hacker News threads
- May 2018Deep Learning with Limited Numerical Precision
- May 2015Fast Approximate Logarithms, Part I: The Basics
- Sep 2015Why Are Eight Bits Enough for Deep Neural Networks?
- Nov 2015TensorFlow: open-source library for machine intelligence
- Feb 2017The rise of AI is creating new variety in the chip market, and trouble for Intel
- Apr 2017An In-Depth Look at Google's Tensor Processing Unit Architecture
- Apr 2017An In-Depth Look at Google's Tensor Processing Unit Architecture
- 455
Measuring AI Ability to Complete Long Software Tasks
Hacker News threads
- Mar 2025Measuring AI Ability to Complete Long Tasks
- Mar 2025Measuring AI Ability to Complete Long Tasks
- Jul 2025Measuring AI Ability to Complete Long Tasks
- Apr 2025Forecaster reacts: METR's bombshell paper about AI acceleration
- May 2025A conversation about AI for science with Jason Pruet
- Oct 2025Beliefs that are true for regular software but false when applied to AI
- Apr 2026Introducing GPT-5.5
- May 2026Ask HN: Why would we care about "extended time horizons" and LLMs?
- May 2026The Sigmoids Won't Save You
- 456
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Hacker News threads
- Jan 2025DeepSeek-V2: A Strong, Economical, and Efficient MOE Language Model
- Jan 2025DeepSeek's multi-head latent attention and other KV cache tricks
- Apr 2025Xiaomi MiMo Reasoning Model
- May 2025Attention Wasn't All We Needed
- Dec 2025Zebra-Llama – Towards efficient hybrid models
- Dec 2025Google Titans architecture, helping AI have long-term memory
- Jun 2026How LLMs Work
- 457
Why Language Models Hallucinate
Hacker News threads
- Sep 2025Why Language Models Hallucinate
- Sep 2025Why Language Models Hallucinate
- Mar 2026Why Language Models Hallucinate (2025)
- Sep 2025OpenAI’s latest research paper demonstrates that falsehoods are inevitable
- Sep 2025What happens when coding agents stop feeling like dialup?
- Oct 2025GPT-5o-mini hallucinates medical residency applicant grades
- Dec 2025Apple's slow AI pace becomes a strength as market grows weary of spending
- Feb 2026Two kinds of AI users are emerging. The gap between them is astonishing
- May 2026OpenAI admits AI hallucinations are mathematically inevitable (Sept. 2025)
- 458
YOLO9000: Better, Faster, Stronger
Hacker News threads
- Jul 2020YOLO9000: Better, Faster, Stronger
- Dec 2016YOLO9000: Better, Faster, Stronger
- Jun 2017Supercharge your Computer Vision models with the TensorFlow Object Detection API
- Jul 2017CVPR 2017 Best Paper Awards
- Aug 2017YOLO: Real-Time Object Detection
- Nov 2017Using CNNs for Handbag Brand and Color Detection
- Nov 2017An intuitive explanation of the SSD MultiBox object detection technique
- Mar 2020The End of Starsky Robotics
- 459
Were RNNs All We Needed?
Hacker News threads
- 460
Deep Learning is Not So Mysterious or Different
Hacker News threads
- Mar 2025Deep Learning Is Not So Mysterious or Different
- Aug 2026Deep Learning Is Not So Mysterious or Different
- Mar 2025Deep Learning Is Not So Mysterious or Different
- Apr 2025Are polynomial features the root of all evil? (2024)
- Aug 2025Do we understand how neural networks work?
- Apr 2026There Will Be a Scientific Theory of Deep Learning
- May 2026A Theory of Deep Learning
- Sep 2026Transformers Explained Visually
- 461
More Agents Is All You Need
Hacker News threads
- Apr 2024More Agents Is All You Need: LLMs performance scales with the number of agents
- Feb 2024More Agents Is All You Need
- Feb 2024More Agents Is All You Need
- Mar 2024Claude 3 beats GPT-4 on Aider's code editing benchmark
- Apr 2024Storm: LLM system that researches a topic and generates full-length wiki article
- Aug 2024AI agents but they're working in big tech
- Sep 2024Learning to Reason with LLMs
- Jan 2025Agents Are Not Enough
- 462
Harnessing the Universal Geometry of Embeddings
Hacker News threads
- May 2025Harnessing the Universal Geometry of Embeddings
- Sep 2026Harnessing the Universal Geometry of Embeddings
- May 2025Text Embeddings are All Alike
- Dec 2025The universal weight subspace hypothesis
- Jan 2026Moltbook
- Mar 2026
- Jul 2026Emily Bender Sets the Record Straight on "Stochastic Parrots"
- Aug 2026Models Are Getting Dumber on Purpose
- 463
Design Patterns for Securing LLM Agents against Prompt Injections
Hacker News threads
- Aug 2025Design Patterns for Securing LLM Agents Against Prompt Injections
- Jul 2025Design Patterns for Securing LLM Agents Against Prompt Injections
- Aug 2025Design Patterns for Securing LLM Agents Against Prompt Injections
- Jun 2025Design Patterns for Securing LLM Agents Against Prompt Injections
- Jul 2025Supabase MCP can leak your entire SQL database
- Aug 2025My Lethal Trifecta talk at the Bay Area AI Security Meetup
- Sep 2025Launch HN: Slashy (YC S25) – AI that connects to apps and does tasks
- Jul 2026Leaking YouTube Creators Private Videos
- 464
Learning Transferable Architectures for Scalable Image Recognition
Hacker News threads
- Jul 2017Learning Transferable Architectures for Scalable Image Recognition
- Sep 2017Machine learning optimization of machine learning architecture
- Jul 2017Learning Transferable Architectures for Scalable Image Recognition
- Aug 2017YOLO: Real-Time Object Detection
- Sep 2017Where will artificial general intelligence come from?
- Nov 2017Building A.I. That Can Build A.I
- Jul 2018Darts: Differentiable architecture search for convolutional, recurrent networks
- Oct 2018Introducing AdaNet: Fast and Flexible AutoML with Learning Guarantees
- 465
Gemini: A Family of Highly Capable Multimodal Models
Hacker News threads
- Dec 2023Gemini: A Family of Highly Capable Multimodal Models
- Dec 2023Gemini: A Family of Highly Capable Multimodal Models
- Feb 2024The killer app of Gemini Pro 1.5 is using video as an input
- Mar 2024Four new models that are benchmarking near or above GPT-4
- Apr 2024Hello OLMo: A truly open LLM
- May 2024Gemini Nano coming built in to Chrome 126, powered by WebGPU
- Dec 2025Gemini 3 Pro: the frontier of vision AI
- 466
word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method
Hacker News threads
- Feb 2015Word2Vec Explained [pdf]
- Jun 2015Hound voice search NLP demo [video]
- Oct 2015Primer on Neural Network Models for Natural Language Processing[pdf]
- Mar 2017Facebook releases 300-dimensional pretrained Fasttext vectors for 90 languages
- Sep 2017What every software engineer should know about search
- Nov 2017Ask HN: What are some interesting papers in CS for a beginner?
- 467
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Hacker News threads
- Apr 2024Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
- Jul 2023LLaMA2 Chat 70B outperformed ChatGPT
- Oct 2023Show HN: Tonic Validate Metrics – an open-source RAG evaluation metrics package
- Dec 2023Gemini Pro achieves accuracy slightly inferior to GPT 3.5 Turbo
- Apr 2025Chain of Recursive Thoughts: Make AI think harder by making it argue with itself
- Jun 2025LLM code generation may lead to an erosion of trust
- 468
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Hacker News threads
- Jun 2016DeepArt.io introduces style transfer for videos
- Jul 2016Prisma: neural-style instagram filters
- Mar 2017Deep Learning enables hearing aid wearers to pick out a voice in a crowded room
- Jul 2017Prisma’s next AI project is a fun selfie sticker maker called Sticky
- Oct 2017Show HN: Paint yourself in the style of classic art, in your browser
- 469
Do ImageNet Classifiers Generalize to ImageNet?
Hacker News threads
- Apr 2019Ask HN: Dataset Cleaning Tips
- Sep 2019AI competitions don’t produce useful models
- Feb 2021DeepMind achieves SOTA image recognition with 8.7x faster training
- Apr 2021Are deep neural networks dramatically overfitted? (2019)
- Dec 2021A cartel of influential datasets are dominating machine learning research
- 470
Mathematical Capabilities of ChatGPT
Hacker News threads
- Feb 2023Mathematical Capabilities of ChatGPT
- Mar 2023Ask HN: Who wants to be hired? (March 2023)
- Apr 2023Ask HN: Who wants to be hired? (April 2023)
- Apr 2023
- Jun 2023MIT Responds to “ Exploring the MIT Mathematics and EECS Curriculum Using LLMs” [pdf]
- Oct 2023AI is replacing customer service jobs across the globe
- Oct 2023GPT-4 Understands
- Jun 2024Terence Tao on proof checkers and AI programs
- 471
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
Hacker News threads
- Jun 2020Pulse: Self-Supervised Photo Upsampling via Latent Space Exploration
- Jun 2020Facial Recognition Leads To False Arrest Of Black Man In Detroit
- Jul 2020Yann LeCun quits Twitter amid acrimonious exchanges on AI bias
- Feb 2022Recovering redacted information from pixelated videos
- May 2022Imagen, a text-to-image diffusion model
- Dec 2022Pixelmator Pro gets a magical, AI‑powered Deband feature
- 472
Generalization in Deep Learning
Hacker News threads
- Oct 2017Generalization in Deep Learning [pdf]
- Oct 2017RCN is much more data efficient than traditional Deep Neural Networks
- Nov 2017Software 2.0
- Dec 2017Mathematics of Deep Learning [pdf]
- Apr 2021Are deep neural networks dramatically overfitted? (2019)
- Jun 2021GitHub Copilot as open source code laundering?
- 473
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Hacker News threads
- Apr 2024Visual Autoregressive Modeling: Scalable Image Generation W NextScale Prediction
- Oct 2024Visual Autoregressive Modeling: Image Generation via Next-Resolution Prediction
- Oct 2024Faster convergence for diffusion models
- Mar 20254o Image Generation
- Apr 2025No elephants: Breakthroughs in image generation
- Apr 2025No elephants: Breakthroughs in image generation
- May 2025Diffusion models explained simply
- Aug 2025Ask HN: Who wants to be hired? (August 2025)
- 474
One-shot Learning with Memory-Augmented Neural Networks
Hacker News threads
- May 2016One-shot Learning with Memory-Augmented Neural Networks
- Jun 2016The truth about deep learning
- Jun 2016AI, Deep Learning, and Machine Learning: A Primer [video]
- Nov 2016Show HN: DeepRhyme (D-Prime) – Generating dope rhymes with machine learning
- Nov 2016Embed, encode, attend, predict: the new deep learning formula for NLP models
- Dec 2016This AI Boom Will Also Bust
- Dec 2016Open-sourcing DeepMind Lab
- Jun 2018Deep learning: a critical appraisal
- 475
Textbooks Are All You Need II: phi-1.5 technical report
Hacker News threads
- Sep 2023The tide is shifting: 1.3B outperforms 7B Llama 2
- Sep 2023Textbooks Are All You Need II: phi-1.5 technical report
- Sep 2023Large Language Models for Compiler Optimization
- Sep 2023Outperforming LLMs with less training data and smaller model sizes
- Oct 2023AI hype is built on high test scores. Those tests are flawed
- Nov 2023A Coder Considers the Waning Days of the Craft
- Nov 2023MonadGPT – What would have happened if ChatGPT was invented in the 17th century?
- Jan 2024Microsoft Phi-2 model changes licence to MIT
- Jan 2024Ten Noteworthy AI Research Papers of 2023
- Jan 2024A Philosophical Introduction to Language Models
Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.