Hacker Papers

1. 101
   

   Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training

   Hong Liu et al. · 2023

   Hacker News threads

   • Apr 2024Sophia: Scalable Stochastic 2nd-Order Optimizer for Language Model Pre-Training
   • May 2023Sophia: A Scalable Stochastic Second-Order Optimizer
   • Jul 2023Sophia: A Scalable Stochastic Optimizer for Language Model Pre-Training
   • May 2023MITx Differential Equations starts May 31
   • Jun 2023Notes on training BERT from scratch on an 8GB consumer GPU
   • Jun 2023Notes on training BERT from scratch on an 8GB consumer GPU
   • Aug 2023Risky Giant Steps Can Solve Optimization Problems Faster

   arXiv ↗
2. 102
   

   BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

   Junnan Li et al. · 2023

   Hacker News threads

   • Jan 2023Blip-2
   • Mar 2023Zero-1-to-3: Zero-shot One Image to 3D Object
   • Apr 2023MiniGPT-4
   • Apr 2023MiniGPT-4
   • May 2023MaMMUT: A simple vision-encoder text-decoder architecture for multimodal tasks

   arXiv ↗
3. 103
   

   Tighter Bounds on the Expressivity of Transformer Encoders

   David Chiang et al. · 2023

   Hacker News threads

   • Apr 2023Tighter bounds on the expressivity of transformer encoders
   • Jun 2023Thinking Like Transformers (pdf)
   • Jun 2023Researchers warn of ‘model collapse’ as AI trains on AI-generated content
   • Dec 2023Ask HN: AI/ML papers to catch up with current state of AI?
   • Jan 2024Turing Complete Transformers: Two Transformers Are More Powerful Than One

   arXiv ↗
4. 104
   

   Studying Large Language Model Generalization with Influence Functions

   Roger Grosse et al. · 2023

   Hacker News threads

   • Apr 2024Studying Large Language Model Generalization with Influence Functions
   • Nov 2023HN thread 38149093
   • Dec 2023Googlers cracked an SF rival's tech model with a single word
   • Dec 2023Sorry, but a new prompt for GPT-4 is not a paper
   • Jul 2026Andrew Kelley: Don't Take the Black Pill

   arXiv ↗
5. 105
   

   The Grand Illusion: The Myth of Software Portability and Implications for ML Progress

   Fraser Mince et al. · 2023

   Hacker News threads

   • Mar 2024The Myth of Software Portability and Implications for ML Progress (2023)
   • Sep 2023The Myth of Software Portability and Implications for ML Progress
   • Oct 2023SiFive Rolls Out RISC-V Cores Aimed at Generative AI and ML
   • Jan 2024Google TPU v5p beats Nvidia H100
   • Sep 2024Show HN: Tune LLaMa3.1 on Google Cloud TPUs
   • Sep 2024We fine-tuned Llama 405B on AMD GPUs

   arXiv ↗
6. 106
   

   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 ↗
7. 107
   

   Starlink Generation 2 Mini Satellites: Photometric Characterization

   Anthony Mallama et al. · 2023

   Hacker News threads

   • Jun 2023Starlink v2 reached the brightness reduction target recommended by astronomers
   • Sep 2023SpaceX projected 20M Starlink users by 2022–it ended up with 1M
   • Apr 2024LSST Camera: largest camera for astronomy
   • Apr 2025An image of the Australian desert illuminates satellite pollution

   arXiv ↗
8. 108
   

   Large Language Models as Optimizers

   Chengrun Yang et al. · 2023

   Hacker News threads

   • Sep 2023Large Language Models as Optimizers. +50% on Big Bench Hard
   • Sep 2023A New Age of Magic
   • Jan 2024Is the ChatGPT API Refusing to Summarize Academic Papers?
   • Oct 2026Claude reveals ECDSA curve origins

   arXiv ↗
9. 109
   

   Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle

   Rylan Schaeffer et al. · 2023

   Hacker News threads

   • Apr 2025Double Descent Demystified: size of smallest non-zero singular value of X
   • Sep 2024Double Descent Demystified
   • Apr 2023Double Descent in Human Learning
   • Mar 2024Learning Theory from First Principles [pdf]
   • Jul 2024The Truth About Linear Regression (2015)

   arXiv ↗
10. 110
    

    MusicLM: Generating Music From Text

    Andrea Agostinelli et al. · 2023

    Hacker News threads

    • Jan 2023MusicLM: Generating Music from Text
    • Jan 2023MusicLM: Generating Music from Text
    • May 2023Google makes its text-to-music AI public
    • Jul 2025Introduction to Computer Music

    arXiv ↗
11. 111
    

    The Poison of Alignment

    Aibek Bekbayev et al. · 2023

    Hacker News threads

    • Aug 2023The Poison of (LLMs) Alignment
    • Aug 2023The Poison of Alignment
    • Aug 2023The Poison of Alignment
    • Sep 2023Study shows over time, ChatGPT lost accuracy
    • Jun 2024Cost of self hosting Llama-3 8B-Instruct
    • Jan 2025DeepSeek's Hidden Bias: How We Cut It by 76% Without Performance Loss

    arXiv ↗
12. 112
    

    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 ↗
13. 113
    

    Power Hungry Processing: Watts Driving the Cost of AI Deployment?

    Alexandra Sasha Luccioni et al. · 2023

    Hacker News threads

    • Apr 2024Power Hungry Processing: Watts Driving the Cost of AI Deployment?
    • Dec 2023Making an image with generative AI uses as much energy as charging your phone
    • Feb 2024Paragraph Pollution: AI is (probably) greener than you typing on a laptop
    • Apr 2024When Will the GenAI Bubble Burst?

    arXiv ↗
14. 114
    

    Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

    Chengyi Wang et al. · 2023

    Hacker News threads

    • Jan 2023Neural Codec Language Models Are Zero-Shot Text to Speech Synthesizers
    • Jan 2023Will TTS and STT benefit from the AI boom?
    • Feb 2023I had ChatGPT write a Decemberists song
    • Sep 2024Amazon's Secret Weapon in Chip Design Is Amazon

    arXiv ↗
15. 115
    

    Mastering Diverse Domains through World Models

    Danijar Hafner et al. · 2023

    Hacker News threads

    • Jan 2023Mastering Diverse Domains Through World Models
    • Jan 2023Google’s DeepMind: Mastering Diverse Domains Through World Models
    • Jul 2023Ask HN: Who is hiring? (July 2023)
    • Apr 2025DeepMind program finds diamonds in Minecraft without being taught

    arXiv ↗
16. 116
    

    How Language Model Hallucinations Can Snowball

    Muru Zhang et al. · 2023

    Hacker News threads

    • May 2023How Language Model Hallucinations Can Snowball
    • May 2023A Logic for Expressing Transformers
    • Sep 2025An LLM is a lossy encyclopedia
    • Dec 2025Project Vend: Phase Two

    arXiv ↗
17. 117
    

    SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression

    Tim Dettmers et al. · 2023

    Hacker News threads

    • Jun 2023SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
    • Jun 2023LLM.int8(): 8-Bit Matrix Multiplication for Transformers at Scale
    • Sep 2023ROCm Is AMD's #1 Priority, Executive Says
    • Mar 2024Fine tune a 70B language model at home

    arXiv ↗
18. 118
    

    In-Context Learning Creates Task Vectors

    Roee Hendel et al. · 2023

    Hacker News threads

    • Oct 2023In-Context Learning Creates Task Vectors
    • Oct 2023LLMs playing chess are sensitive to how the position came to be
    • Nov 2024Task Vectors [in Vision and Language Models (VLM's)] Are Cross-Modal
    • Dec 2025Ask HN: How can I get better at using AI for programming?

    arXiv ↗
19. 119
    

    Scaling Laws for Generative Mixed-Modal Language Models

    Armen Aghajanyan et al. · 2023

    Hacker News threads

    • Feb 2023Planning for AGI and Beyond
    • Mar 2023Google Releases Paper on Embodied LLM (562b parameters)
    • Apr 2025Liquid: Language models are scalable and unified multi-modal generators

    arXiv ↗
20. 120
    

    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 ↗
21. 121
    

    G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment

    Yang Liu et al. · 2023

    Hacker News threads

    • Jun 2023The Darwinian argument for worrying about AI
    • Dec 2024Garvata: Observability and Debugging for AI Agent Stack
    • May 2025Positional preferences, order effects, prompt sensitivity undermine AI judgments

    arXiv ↗
22. 122
    

    Visual Instruction Tuning

    Haotian Liu et al. · 2023

    Hacker News threads

    • Dec 2023Vowels and Diphthongs in Sperm Whales
    • Apr 2024Suggest HN: Rabbit r1 AI device for blind or visually impaired people?
    • May 2024PaliGemma: Open-Source Multimodal Model by Google

    arXiv ↗
23. 123
    

    Simple and Controllable Music Generation

    Jade Copet et al. · 2023

    Hacker News threads

    • Jun 2023MusicGen-Looper: Generate fixed-bpm loops from text prompts
    • Mar 2025Show HN: Sonauto API – Generative music for developers
    • Oct 2025Should LLMs just treat text content as an image?

    arXiv ↗
24. 124
    

    Efficient Guided Generation for Large Language Models

    Brandon T. Willard, Rémi Louf · 2023

    Hacker News threads

    • Aug 2023Show HN: LLMs can generate valid JSON 100% of the time
    • May 2024Mistral Fine-Tune
    • Jan 2026LLM Structured Outputs Handbook

    arXiv ↗
25. 125
    

    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.