Hacker Papers

1. 851
   

   The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink

   David Patterson et al. · 2022

   Hacker News threads

   • Apr 2022The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink
   • Jan 2023On the dangers of stochastic parrots: Can language models be too big? (2021)
   • Jul 2025Mistral reports on the environmental impact of LLMs
   • Aug 2025Google agrees to pause AI workloads when power demand spikes
   • Aug 2025In a first, Google has released data on how much energy an AI prompt uses

   arXiv ↗
2. 852
   

   The Impact of Positional Encoding on Length Generalization in Transformers

   Amirhossein Kazemnejad et al. · 2023

   Hacker News threads

   • Jun 2023The Impact of Positional Encoding on Length Generalization in Transformers
   • Aug 2024The Impact of Positional Encoding on Length Generalization in Transformers
   • Apr 2025The Llama 4 herd
   • Apr 2025Llama 4 Now Live on Groq
   • Jul 2025LLM Embeddings Explained: A Visual and Intuitive Guide
   • Oct 2026Is 'Attention' the Essence of Intelligence?

   arXiv ↗
3. 853
   

   Competition-Level Code Generation with AlphaCode

   Yujia Li et al. · 2022

   Hacker News threads

   • Dec 2022Competition-Level Code Generation with AlphaCode
   • Mar 2022GPT-3 can run code
   • Dec 2022AlphaCode by DeepMind
   • Dec 2022DeepMind’s AlphaCode Conquers Coding, Performing as Well as Humans
   • Jul 2023GPT-Migrate converts repos from one lang/framework to another

   arXiv ↗
4. 854
   

   FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI

   Elliot Glazer et al. · 2024

   Hacker News threads

   • Nov 2024FrontierMath: A benchmark for evaluating advanced mathematical reasoning in AI
   • Nov 2024AlphaProof's Greatest Hits
   • Dec 2024Reimagining mathematics in a world of reasoning machines [video]
   • Feb 2025Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving [pdf]

   arXiv ↗
5. 855
   

   Complete Chess Games Enable LLM Become A Chess Master

   Yinqi Zhang et al. · 2025

   Hacker News threads

   • Aug 2025LLMs aren't world models
   • Feb 2026Claude Sonnet 4.6 System Card
   • Feb 2026Stop Thinking of AI as a Coworker. It's an Exoskeleton
   • Jun 2026I used Claude Code to get a second opinion on my MRI

   arXiv ↗
6. 856
   

   Bringing GNU Emacs to Native Code

   Andrea Corallo et al. · 2020

   Hacker News threads

   • May 2021Bringing GNU Emacs to Native Code (2020)
   • Sep 2022Bringing GNU Emacs to Native Code
   • May 2020Bringing GNU Emacs to native code [video]
   • Jul 2020Bump Emacs Version to 27.1
   • May 2021TIL: Tcl-inspired command language on top of D

   arXiv ↗
7. 857
   

   Student of Games: A unified learning algorithm for both perfect and imperfect information games

   Martin Schmid et al. · 2021

   Hacker News threads

   • Dec 2021Player of Games
   • Jan 2022How A.I. Conquered Poker
   • Jul 2022Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning
   • Dec 2023Show HN: Easily train AlphaZero-like agents on any environment you want!

   arXiv ↗
8. 858
   

   Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

   David Raposo et al. · 2024

   Hacker News threads

   • Apr 2024Mixture-of-Depths: Dynamically allocating compute in transformers
   • Apr 2024Mixture-of-Depths: Dynamically allocating compute in transformer language models
   • Apr 2024Mixture-of-Depths: Dynamically allocating compute in transformers
   • Apr 2024Show HN: Speeding up LLM inference 2x times (possibly)
   • Aug 2024Antifragility in complex dynamical systems
   • Sep 2026GPT-6 Astra, looped transformers, and hidden reasoning

   arXiv ↗
9. 859
   

   Kek, Cucks, and God Emperor Trump: A Measurement Study of 4chan's Politically Incorrect Forum and Its Effects on the Web

   Gabriel Emile Hine et al. · 2016

   Hacker News threads

   • Oct 2016A Study of 4chan’s Politically Incorrect Forum and its Effect on the Web
   • Oct 2016Study of 4chan's Politically Incorrect Forum and Its Effect on the Web
   • Oct 2016A Longitudinal Measurement Study of 4chan’s Politically Incorrect Forum
   • Jan 2017An Analysis of Anonymity and Ephemerality in 4chan /b/ (2011) [pdf]
   • Jun 2017A Study of 4chan’s Politically Incorrect Forum and Its Effects on the Web [pdf]
   • Jul 2022Study finds Wikipedia influences judicial behavior

   arXiv ↗
10. 860
    

    Delving into LLM-assisted writing in biomedical publications through excess vocabulary

    Dmitry Kobak et al. · 2024

    Hacker News threads

    • Jun 2024Delving into ChatGPT usage in academic writing through excess vocabulary
    • Jun 2024Delving into ChatGPT usage in academic writing through excess vocabulary
    • Jul 2024Diving into deep learning: Understanding Deep Learning book review [pdf]
    • Aug 2024Ask HN: Why does ChatGPT love the word "eager" so much?
    • Jan 2026Ask HN: How can you instantly tell something was written by AI?

    arXiv ↗
11. 861
    

    Improved Techniques for Training GANs

    Tim Salimans et al. · 2016

    Hacker News threads

    • Jun 2016Improved Techniques for Training GANs – OpenAI's first paper
    • Jun 2016Generative Models
    • Aug 2016OpenAI Team Update
    • Jan 2017Game Theory Reveals the Future of Deep Learning

    arXiv ↗
12. 862
    

    Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning

    Felipe Petroski Such et al. · 2017

    Hacker News threads

    • Dec 2017Genetic Algorithms for Training Deep Neural Networks for Reinforcement Learning
    • Dec 2017Evolving Simple Organisms
    • Jun 2018Playing Atari with Six Neurons
    • Jul 2018Deep Learning and Free Software

    arXiv ↗
13. 863
    

    SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver

    Po-Wei Wang et al. · 2019

    Hacker News threads

    • Jun 2019SATNet: Bridging deep learning and logical reasoning with differentiable SAT
    • May 2020Symbolic mathematics finally yields to neural networks
    • Jun 2020Deep Learning – The “Why” Question (2018)
    • Dec 2022Do Simpler Machine Learning Models Exist and How Can We Find Them?

    arXiv ↗
14. 864
    

    Classic Nintendo Games are (Computationally) Hard

    Greg Aloupis et al. · 2012

    Hacker News threads

    • Nov 2015Classic Nintendo Games Are NP-Hard (2012)
    • Mar 2012Classic Nintendo Games are (NP-)Hard
    • Mar 2012Classic Nintendo Games are (NP-)Hard
    • Sep 2017The N-Queens completion problem is NP-hard
    • Dec 2017Classic Nintendo Games Are NP-Hard (2012)
    • Aug 2019How Command and Conquer: Tiberian Sun punished the computers of the day [video]

    arXiv ↗
15. 865
    

    Robust Physical-World Attacks on Deep Learning Models

    Kevin Eykholt et al. · 2017

    Hacker News threads

    • Jul 2017Robust Physical-World Attacks on Machine Learning Models
    • Mar 2020Robust Physical-World Attacks on Deep Learning Models (2018)
    • Feb 2018Chinese police don high-tech glasses to nab suspects
    • Mar 2018LiDAR scans are finding hidden Roman roads and cutting crime
    • Feb 2020Hackers tricked Teslas into speeding with 2-inch strip of tape on a 35-MPH sign

    arXiv ↗
16. 866
    

    Hierarchical Transformers Are More Efficient Language Models

    Piotr Nawrot et al. · 2021

    Hacker News threads

    • Nov 2021Hierarchical transformers are more efficient language models
    • Nov 2021Transformers from Scratch
    • Mar 2023CoLT5: Faster Long-Range Transformers With Conditional Computation
    • Apr 2023From Deep to Long Learning

    arXiv ↗
17. 867
    

    The Spy in the Sandbox -- Practical Cache Attacks in Javascript

    Yossef Oren et al. · 2015

    Hacker News threads

    • Mar 2015The Spy in the Sandbox: Practical Cache Attacks in JavaScript
    • Apr 2015The Spy in the Sandbox – Practical Cache Attacks in JavaScript
    • Apr 2015Using JavaScript to Read L3 CPU Cache [pdf]
    • Jul 2016The Browser Is the Worst Sandbox Ever Designed
    • Apr 2017Blink-dev – Intent to Ship: SharedArrayBuffer
    • Sep 2017LLVM 5.0.0 Release

    arXiv ↗
18. 868
    

    From Philosophy to Program Size

    G. J. Chaitin · 2003

    Hacker News threads

    • Feb 2017From Philosophy to Program Size (2003)
    • Mar 2017Why literature is the ultimate big-data challenge
    • Sep 2017Ask HN: CS as a philosophy
    • Jul 2026How real are real numbers? (2004)

    arXiv ↗
19. 869
    

    Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution

    Judea Pearl · 2018

    Hacker News threads

    • Jan 2018Theoretical Impediments to Machine Learning with Seven Sparks from Causality
    • Jan 2018Alibaba neural network defeats human in global reading test
    • Apr 2018Artificial Intelligence with Erlang: The Domain of Relatives (2007)
    • Jul 2025AGI Is Mathematically Impossible (3): Kolmogorov Complexity

    arXiv ↗
20. 870
    

    Fansmitter: Acoustic Data Exfiltration from (Speakerless) Air-Gapped Computers

    Mordechai Guri et al. · 2016

    Hacker News threads

    • Jun 2016Fansmitter: Acoustic Data Exfiltration from Speakerless Air-Gapped Computers
    • Jul 2017The Adventures of AV and the Leaky Sandbox [pdf]
    • Jul 2025AI comes up with bizarre physics experiments, but they work
    • Dec 2025How I discovered a hidden microphone on a Chinese NanoKVM

    arXiv ↗
21. 871
    

    PathNet: Evolution Channels Gradient Descent in Super Neural Networks

    Chrisantha Fernando et al. · 2017

    Hacker News threads

    • Feb 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networks
    • Feb 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networks
    • Mar 2017DeepMind's PathNet – potentially describing how general AI will look like
    • Feb 2017DeepMind just published a mind blowing paper: PathNet
    • Mar 2017Elon Musk’s Neuralink wants to boost the brain to keep up with AI
    • Jun 2020Neurons that fire together, wire together, but how?

    arXiv ↗
22. 872
    

    Deep Voice: Real-time Neural Text-to-Speech

    Sercan O. Arik et al. · 2017

    Hacker News threads

    • Mar 2017Deep Voice: Real-Time Neural Text-To-Speech (2017)
    • Feb 2017Deep Voice: Real-Time Neural Text-To-Speech
    • Feb 2017Deep Voice: Real-Time Neural Text-To-Speech for Production
    • Mar 2017Deep Voice: Real-Time Neural Text-To-Speech
    • Oct 2024Were RNNs all we needed?

    arXiv ↗
23. 873
    

    When Will AI Exceed Human Performance? Evidence from AI Experts

    Katja Grace et al. · 2017

    Hacker News threads

    • May 2017When Will Machines Exceed Human Performance? Survey of ML Researchers.
    • May 2017When Will AI Exceed Human Performance? Evidence from AI Experts
    • May 2017AlphaGo's next move
    • Oct 2017There's No Fire Alarm for Artificial General Intelligence
    • Mar 2021Multimodal Neurons in Artificial Neural Networks

    arXiv ↗
24. 874
    

    Relational inductive biases, deep learning, and graph networks

    Peter W. Battaglia et al. · 2018

    Hacker News threads

    • Oct 2018Relational inductive biases, deep learning, and graph networks
    • Dec 2024Relational inductive biases, deep learning, and graph networks
    • Jun 2018Chatbots were the next big thing: what happened?
    • Aug 20182018 Fields Medal and Nevanlinna Prize Winners
    • Aug 2019Model-Based Reinforcement Learning for Atari

    arXiv ↗
25. 875
    

    ATLAS: Learning to Optimally Memorize the Context at Test Time

    Ali Behrouz et al. · 2025

    Hacker News threads

    • May 2025Atlas: Learning to Optimally Memorize the Context at Test Time
    • Dec 2025Google Titans architecture, helping AI have long-term memory
    • Jan 2026The Q, K, V Matrices
    • Apr 2026Show HN: AI memory with biological decay (52% recall)

    arXiv ↗

Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.