Hacker Papers
- 626
A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers
Hacker News threads
- Jun 2025The bitter lesson is coming for tokenization
- Aug 2025Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
- Aug 2025Is chain-of-thought AI reasoning a mirage?
- Oct 2025Less is more: Recursive reasoning with tiny networks
- Sep 2026GPT-6 Astra, looped transformers, and hidden reasoning
- 627
Mass Extinction And The Structure Of The Milky Way
Hacker News threads
- May 2017Mass Extinction and the Structure of the Milky Way (2013)
- Oct 2019Mass Extinction and the Structure of the Milky Way
- Sep 2013Correlations between mass extinctions, sun's changing position in galaxy
- Jan 2017Large stationary gravity wave in the atmosphere of Venus
- Mar 2018All disk galaxies rotate once every billion years: study
- Oct 2018Panspermia
- May 2020Swarm satellites probe weakening of Earth’s magnetic field
- 628
Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches
Hacker News threads
- Jul 2019A Worrying Analysis of Recent Neural Recommendation Approaches
- Aug 2019Are We Making Much Progress? Analysis of Recent Neural Recommendation Approaches
- Jul 2019Are We Making Much Progress with Neural Networks?
- Dec 2019Categories of deep recommendation systems
- Aug 2020Language-Agnostic Bert Sentence Embedding
- Mar 2021AI skills are worth less than you think (2019)
- Jul 2021Deep reinforcement learning is a waste of time (2019)
- 629
YOLOv4: Optimal Speed and Accuracy of Object Detection
Hacker News threads
- Apr 2020YOLOv4: Optimal Speed and Accuracy of Object Detection
- Apr 2020YOLOv4: Optimal Speed and Accuracy of Object Detection
- May 2020Training YOLOv4 on a Custom Dataset
- Jun 2020YOLOv5: State-of-the-art object detection at 140 FPS
- Dec 2021Pine64 and Radxa's new Pi CM4-compatible boards
- May 2022DeepMind: A Generalist Agent
- 630
It's Time to Replace TCP in the Datacenter
Hacker News threads
- Nov 2024It's time to replace TCP in the datacenter (2023)
- Oct 2022It's time to replace TCP in the Datacenter
- Nov 2022Moving past TCP in the data center, part 2
- Feb 2023Is It Time to Replace TCP in Data Centers?
- May 2023Unbounded memory usage by Linux TCP for receive buffers, and how we fixed it
- Oct 2023HN thread 38049303
- 631
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Hacker News threads
- Feb 2015Batch Normalization: Accelerating Deep Network Training [pdf]
- Feb 2015Ioffe and Szegedy get 4.8% top-5 test on ImageNet(beating recent MSR result)
- Feb 2026Batch Normalization: Accelerating Deep Network Training (2015)
- May 2015The state of Computer Vision and AI: we are really, really far (2012)
- Apr 2016Tinker with a Neural Network in Your Browser
- Aug 2016Some of the most important deep learning papers
- Mar 2017Deep Forest: Towards an Alternative to Deep Neural Networks
- 632
Resource Polymorphism
Hacker News threads
- 633
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Hacker News threads
- 634
The JPEG XL Image Coding System: History, Features, Coding Tools, Design Rationale, and Future
Hacker News threads
- Jul 2025The JPEG XL Image Coding History, Features, Coding Tools, Design Rationale
- Jun 2025The JPEG XL Image Coding System
- Jul 2025JPEG XL Coding System: History, Features, Tools, Design Rationale and Future
- Mar 2026JPEG Compression
- Aug 2026Firefox 157 will include JPEG XL by default on all platforms
- Sep 2026The case against JPEG XL
- Oct 2026Shipping JPEG XL in Chrome
- 635
Observing Ultra-High Energy Cosmic Rays with Smartphones
Hacker News threads
- May 2016Observing Ultra-High Energy Cosmic Rays with Smartphones (2014)
- Oct 2014Cosmic rays found in smartphones
- May 2017LHC Micro Models: Build Your Own Particle Detector
- Nov 2018For a brief period, the Windows kernel tried to deal with gamma rays
- Feb 2021Researchers explore how storms on Earth create extreme bursts of radiation
- 636
The Illusion of State in State-Space Models
Hacker News threads
- Jun 2024The illusion of state in state-space models
- Apr 2024The illusion of state in state-space models
- Apr 2024The Illusion of State in State-Space Models
- May 2024Meta AI chief says large language models will not reach human intelligence
- Jun 2024Mamba-2 – State Space Duality
- Oct 2024Were RNNs all we needed?
- Jan 2025RWKV Language Model
- 637
Fast exact summation using small and large superaccumulators
Hacker News threads
- 638
Efficient Memory Management for Large Language Model Serving with PagedAttention
Hacker News threads
- Sep 2023Efficient Memory Management for Large Language Model Serving with PagedAttention
- Apr 2025Efficient Memory Management for Large Language Model Serving with PagedAttention
- Mar 2024LLMs use a surprisingly simple mechanism to retrieve some stored knowledge
- May 2024Gemini Flash
- Jan 2025Qwen2.5-1M: Deploy your own Qwen with context length up to 1M tokens
- Feb 2026Nano-vLLM: How a vLLM-style inference engine works
- 639
Teaching Machines to Read and Comprehend
Hacker News threads
- Jun 2015DeepMind: Teaching Machines to Read and Comprehend
- Jun 2015Teaching Machines to Read and Comprehend – Deepmind [pdf]
- Jun 2015Google Deepmind – Teaching Machines to Read and Comprehend [pdf]
- Jun 2015DeepMind uses the Daily Mail as a huge training corpus for text comprehension
- Dec 2015Teaching Machines to Read and Comprehend [pdf]
- Feb 2016Go, Marvin Minsky, and the Chasm That AI Hasn’t yet Crossed
- May 2016IBM is not doing "cognitive computing" with Watson
- 640
Skip-Thought Vectors
Hacker News threads
- 641
The Design and Implementation of XiaoIce, an Empathetic Social Chatbot
Hacker News threads
- 642
The impossibility of "fairness": a generalized impossibility result for decisions
Hacker News threads
- Aug 2021The impossibility of fairness: a generalized impossibility result for decisions
- Jul 2022The impossibility of “fairness”:a generalized impossibility result for decisions
- Jun 2018AI at Google: our principles
- Feb 2020Setting fairness goals with the TensorFlow constrained optimization library
- Feb 2022How can minorities of regular individuals overturn social conventions?
- Mar 2023Responsible AI Challenge
- 643
CRN++: Molecular Programming Language
Hacker News threads
- 644
What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models
Hacker News threads
- Jul 2025LLMs fail to demonstrate internal world model, according to Harvard/MIT study
- Jul 2025AGI Is Mathematically Impossible (3): Kolmogorov Complexity
- Aug 2025Persona vectors: Monitoring and controlling character traits in language models
- Oct 2025Andrej Karpathy – It will take a decade to work through the issues with agents
- Jun 2026ΠFS
- 645
Indexing dif/2
Hacker News threads
- May 2018Pure efficient “if” in Prolog
- May 2017Ask HN: Why isn't Prolog more popular?
- Oct 2019Swish: SWI Prolog Notebook
- Sep 2022Lunatic: Erlang-Inspired Runtime for WebAssembly
- Dec 2022Prolog at Work
- 646
Logical Induction
Hacker News threads
- 647
Quantum attacks on Bitcoin, and how to protect against them
Hacker News threads
- Nov 2017Quantum attacks on Bitcoin, and how to protect against them [pdf]
- Dec 2017Quantum attacks on Bitcoin, and how to protect against them (ECDSA, SHA256)
- Jul 2019Quantum attacks on Bitcoin, and how to protect against them
- Nov 2017Ask HN: Where do you think Bitcoin will be by 2020?
- Jan 2018NIST Post-Quantum Cryptography Round 1 Submissions
- Apr 2018Quantum Computers Pose Imminent Threat to Bitcoin Security
- Jun 2018I'm Scott Aaronson, quantum computing/computational complexity researcher. AMA
- 648
Forecasting timelines of quantum computing
Hacker News threads
- 649
Quantum theory based on real numbers can be experimentally falsified
Hacker News threads
- Jan 2021Quantum physics needs complex numbers
- Mar 2021Quantum physics needs complex numbers (2021)
- Mar 2021Imaginary Numbers May Be Essential for Describing Reality
- Aug 2021Banach-Tarski and the Paradox of Infinite Cloning
- Apr 2023Quantum Physics Falls Apart Without Imaginary Numbers
- Feb 2026Mathematicians disagree on the essential structure of the complex numbers
- 650
Efficient Training of Language Models to Fill in the Middle
Hacker News threads
Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.