Hacker Papers

1. 701
   

   Automatic Full Compilation of Julia Programs and ML Models to Cloud TPUs

   Keno Fischer, Elliot Saba · 2018

   Hacker News threads

   • Oct 2018Automatic Full Compilation of Julia Programs and ML Models to Cloud TPUs
   • Oct 2018Compiling Julia to TPUs [pdf]
   • Oct 2018Automatic Compilation of Julia Programs and Generic ML Models to Cloud TPUs
   • Jan 2019High Performance Numeric Programming with Swift: Explorations and Reflections
   • Feb 2019Differentiating SSA-Form Programs in Julia (2018) [pdf]
   • Feb 2019Julia on Google TPU: Shakespeare RNN
   • Jul 2019A Differentiable Programming System to Bridge ML and Scientific Computing

   arXiv ↗
2. 702
   

   Artistic style transfer for videos

   Manuel Ruder et al. · 2016

   Hacker News threads

   • May 2016Artistic Style Transfer for Video
   • Jul 2016Artistic style transfer for videos
   • May 2016Artistic style transfer for videos [video]
   • May 2016Artistic style transfer for videos
   • Jun 2016DeepArt.io introduces style transfer for videos
   • Jul 2016Prisma: neural-style instagram filters

   arXiv ↗
3. 703
   

   Learning to Search Better Than Your Teacher

   Kai-Wei Chang et al. · 2015

   Hacker News threads

   • Mar 2016Lee Sedol Beats AlphaGo in Game 4
   • Mar 2016FlappyBird hack using Deep Q-Learning
   • May 2016SyntaxNet: Neural Models of Syntax
   • Jun 2016Intro to Hidden Markov Models (2010) [pdf]

   arXiv ↗
4. 704
   

   Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

   Shaoqing Ren et al. · 2015

   Hacker News threads

   • Aug 2017YOLO: Real-Time Object Detection
   • Oct 2017Show HN: Vehicle Detection – using machine learning and computer vision
   • Nov 2017Using CNNs for Handbag Brand and Color Detection
   • Nov 2017Confession as an AI researcher; seeking advice

   arXiv ↗
5. 705
   

   Prompt Injection as Role Confusion

   Charles Ye et al. · 2026

   Hacker News threads

   • Apr 2026Claude mixes up who said what and that's not OK
   • Jul 2026The Session You Cannot take with you
   • Aug 2026Now we have a timeline of the OpenAI accidental attack against Hugging Face
   • Aug 2026Stealing Reasoning Traces from Proprietary LLM APIs

   arXiv ↗
6. 706
   

   LLMs Get Lost In Multi-Turn Conversation

   Philippe Laban et al. · 2025

   Hacker News threads

   • May 2025LLMs get lost in multi-turn conversation
   • May 2025The unreasonable effectiveness of an LLM agent loop with tool use
   • Jul 2025The new skill in AI is not prompting, it's context engineering
   • Dec 2025The "confident idiot" problem: Why AI needs hard rules, not vibe checks

   arXiv ↗
7. 707
   

   Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B

   Di Zhang et al. · 2024

   Hacker News threads

   • Jun 2024Accessing Math Solutions via Monte Carlo Self-Refine with LLaMa-3 8B
   • Jun 2024AI Search: The Bitter-Er Lesson
   • Aug 2024Ask HN: Research Papers on Prompt Engineering?
   • Sep 2024Reflection 70B, the top open-source model

   arXiv ↗
8. 708
   

   An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

   Shaojie Bai et al. · 2018

   Hacker News threads

   • Mar 2018TCNs are better than RNNs
   • Mar 2018Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
   • Aug 2018An Empirical Evaluation of Generic CNN and RNN for Sequence Modeling
   • Jun 2018Keras vs PyTorch
   • Aug 2018Ask HN: Convolutional VS Recurrent/LSTM/GRU neural networks
   • Dec 2018What Kagglers Are Using for Text Classification

   arXiv ↗
9. 709
   

   SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration

   Jialong Chen et al. · 2026

   Hacker News threads

   • Mar 2026SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via CI
   • Mar 2026SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via CI
   • Mar 2026Speed at the cost of quality: Study of use of Cursor AI in open source projects
   • May 2026Today I've made the difficult decision to reduce the size of Coinbase by ~14%
   • Jun 2026GLM 5.2 vs. Opus

   arXiv ↗
10. 710
    

    First Proof

    Mohammed Abouzaid et al. · 2026

    Hacker News threads

    • Feb 2026First Proof
    • Feb 2026First Proof
    • Feb 2026Gemini 3 Deep Think
    • Mar 2026A Methodological Critique of "First Proof" (Abouzaid et al., 2026)
    • May 2026A recent experience with ChatGPT 5.5 Pro

    arXiv ↗
11. 711
    

    There Will Be a Scientific Theory of Deep Learning

    Jamie Simon et al. · 2026

    Hacker News threads

    • Apr 2026There Will Be a Scientific Theory of Deep Learning
    • May 2026A Theory of Deep Learning
    • Jun 2026How LLMs Work
    • Sep 2026The Millennium Problems for Biology

    arXiv ↗
12. 712
    

    NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles

    Jiajun Lu et al. · 2017

    Hacker News threads

    • Jul 2017NO Need to Worry about Adversarial Examples for Autonomous Vehicles
    • Jul 2017Robust Physical-World Attacks on Machine Learning Models
    • Aug 2017Slight Street Sign Modifications Can Fool Machine Learning Algorithms
    • Nov 2017How Adversarial Attacks Work

    arXiv ↗
13. 713
    

    Tensor Logic: The Language of AI

    Pedro Domingos · 2025

    Hacker News threads

    • Oct 2025Tensor Logic: The Language of AI
    • Oct 2025Tensor Logic: The Language of AI
    • Oct 2025Towards Logic: The Language of AI
    • Jan 2026Ask HN: What do you plan to read in 2026?
    • Apr 2026There Will Be a Scientific Theory of Deep Learning
    • Jul 2026Show HN: I implemented a neural network in SQL

    arXiv ↗
14. 714
    

    Chain of Draft: Thinking Faster by Writing Less

    Silei Xu et al. · 2025

    Hacker News threads

    • Mar 2025Chain of Draft: Thinking Faster by Writing Less
    • Feb 2025Chain of Draft: Thinking Faster by Writing Less
    • Mar 2025Chain of Draft: Thinking Faster by Writing Less
    • Mar 2025Sketch-of-Thought: Efficient LLM Reasoning
    • May 2025Beyond Semantics: Unreasonable Effectiveness of Reasonless Intermediate Tokens
    • Dec 2025Evaluating chain-of-thought monitorability

    arXiv ↗
15. 715
    

    Position: Categorical Deep Learning is an Algebraic Theory of All Architectures

    Bruno Gavranović et al. · 2024

    Hacker News threads

    • Apr 2024Categorical Deep Learning: An Algebraic Theory of Architectures
    • Apr 2024Symbolica hopes to head off the AI arms race by betting on symbolic models
    • Jun 2024Ask HN: Who is hiring? (June 2024)
    • Aug 2024Alexander Grothendieck

    arXiv ↗
16. 716
    

    What Algorithms can Transformers Learn? A Study in Length Generalization

    Hattie Zhou et al. · 2023

    Hacker News threads

    • Feb 2024What Algorithms Can Transformers Learn? A Study in Length Generalization
    • Feb 2024Every model learned by gradient descent is approximately a kernel machine (2020)
    • Apr 2024What can LLMs never do?
    • Dec 2024Byte Latent Transformer: Patches Scale Better Than Tokens

    arXiv ↗
17. 717
    

    A Taxonomy of Omnicidal Futures Involving Artificial Intelligence

    Andrew Critch, Jacob Tsimerman · 2025

    Hacker News threads

    • Jul 2026A Taxonomy of Omnicidal Futures Involving Artificial Intelligence
    • Jul 2026A Taxonomy of Omnicidal Futures Involving Artificial Intelligence (2025)
    • Jul 2026Fields Medals 2026
    • Sep 2026The Last 24 Hours Are the Opening Scene in a Horror Movie
    • Oct 2026LeCun has "zero concerns" about AI wiping out humanity, recent "rogue" incidents

    arXiv ↗
18. 718
    

    Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

    Yuntao Bai et al. · 2022

    Hacker News threads

    • Aug 2023Training a Helpful and Harmless Assistant with Reinforcement Learning from Human
    • Mar 2023Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA
    • Aug 2023The Poison of (LLMs) Alignment
    • Sep 2023Meta wants its open source AI model to be as capable as OpenAI’s best model

    arXiv ↗
19. 719
    

    Hamiltonian Neural Networks

    Sam Greydanus et al. · 2019

    Hacker News threads

    • Feb 2020Sometimes, requiring explanability is counterproductive
    • Jun 2020Teaching physics to neural networks removes 'chaos blindness'
    • Jul 2020AI in physics: are we facing a scientific revolution?

    arXiv ↗
20. 720
    

    LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition

    Valeriia Cherepanova et al. · 2021

    Hacker News threads

    • Jan 2021LowKey web app tweaks images to thwart facial recognition systems
    • Feb 2021Adversarial.io – Fighting mass image recognition
    • Apr 2021Ask HN: Amyone successfully verify fawkes claims of protection against AI?

    arXiv ↗
21. 721
    

    Addressing "Documentation Debt" in Machine Learning Research: A Retrospective Datasheet for BookCorpus

    Jack Bandy, Nicholas Vincent · 2021

    Hacker News threads

    • Feb 2023Ask HN: Does Google use the text inside gdocs and Gmail for training AI models?
    • Jul 2023The Pile: a dataset for language modeling [pdf]
    • Sep 2023

    arXiv ↗
22. 722
    

    Deep Symbolic Regression for Recurrent Sequences

    Stéphane d'Ascoli et al. · 2022

    Hacker News threads

    • Jan 2022Deep symbolic regression for recurrent sequences
    • Feb 2022I asked GPT-NeoX-20B a hundred arithmetic questions
    • Mar 2022GPT-3 can run code

    arXiv ↗
23. 723
    

    Tracr: Compiled Transformers as a Laboratory for Interpretability

    David Lindner et al. · 2023

    Hacker News threads

    • Feb 2023Why Can't Little Chatty Do Math?
    • Sep 2023I made a transformer by hand (no training)
    • Dec 2023Phi-2: The surprising power of small language models

    arXiv ↗
24. 724
    

    Emergent Linear Representations in World Models of Self-Supervised Sequence Models

    Neel Nanda et al. · 2023

    Hacker News threads

    • Jul 2024Large models of what? Mistaking engineering achievements for linguistic agency
    • Nov 2024Evaluating the world model implicit in a generative model
    • Dec 2024Alignment faking in large language models

    arXiv ↗

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