Hacker Papers
- 76
FNet: Mixing Tokens with Fourier Transforms
Hacker News threads
- May 2024FNet: Mixing Tokens with Fourier Transforms (2021)
- May 2021FNet: Mixing Tokens with Fourier Transforms
- May 2021FNet: Attention may be all you WANT but we you need is good token mixing
- May 2021An Interactive Guide to the Fourier Transform (2012)
- May 2024New attention mechanisms that outperform standard multi-head attention
- May 2024New attention mechanisms that outperform standard multi-head attention
- Feb 2025The FFT Strikes Back: An Efficient Alternative to Self-Attention
- Feb 2025The FFT Strikes Back: An Efficient Alternative to Self-Attention
- Mar 2026TorchLean: Formalizing Neural Networks in Lean
- 77
Acquisition of Chess Knowledge in AlphaZero
Hacker News threads
- Nov 2021Acquisition of Chess Knowledge in AlphaZero
- Nov 2021Acquisition of Chess Knowledge in AlphaZero
- Nov 2021Acquisition of Chess Knowledge in AlphaZero [pdf]
- Nov 2021Acquisition of chess knowledge in AlphaZero
- Nov 2021Acquisition of chess knowledge in AlphaZero
- Dec 2021Can deep learning help mathematicians build intuition?
- Nov 2022Acquisition of chess knowledge in AlphaZero
- Feb 2026Experts Have World Models. LLMs Have Word Models
- 78
Tortured phrases: A dubious writing style emerging in science. Evidence of critical issues affecting established journals
Hacker News threads
- Aug 2021A dubious writing style emerging in science
- Aug 2021Tortured phrases: A dubious writing style emerging in science
- Jun 2023Junk websites filled w AI-generated text pulling in money from programmatic ads
- Dec 2023Tortured conference series thriving in Computer Science
- Aug 2026Research papers using "kidney disappointment" instead of "kidney failure"
- Aug 2026Research papers using "kidney disappointment" instead of "kidney failure"
- Aug 2026Anthropic's 'Watermark' Text Adulteration in Claude Is a Perversion of Writing
- 79
Show Your Work: Scratchpads for Intermediate Computation with Language Models
Hacker News threads
- Jul 2022Show Your Work: Scratchpads For Intermediate Computation With Language Models
- Feb 2022AlphaCode as a dog speaking mediocre English
- Feb 2022I asked GPT-NeoX-20B a hundred arithmetic questions
- Mar 2023ChatGPT has trouble giving an answer before explaining its reasoning
- Nov 2025Claude Opus 4.5
- Apr 2026Talk like caveman
- 80
Petals: Collaborative Inference and Fine-tuning of Large Models
Hacker News threads
- Jul 2026Petals: Collaborative Inference and Fine-Tuning of Large Models
- Mar 2023Petals: Collaborative Inference and Fine-Tuning of Large Models
- Dec 2022Petals is creating a free, distributed network for running text-generating AI
- Jan 2023Petals: Run 100B+ language models at home bit-torrent style
- Jan 2023Petals: Run 100B+ language models at home bit-torrent style
- Jan 2023Ask HN: Can you crowdfund the compute for GPT?
- Feb 2023Running large language models like ChatGPT on a single GPU
- Mar 2023The Most Cited AI Papers in 2022
- 81
The Parallelism Tradeoff: Limitations of Log-Precision Transformers
Hacker News threads
- May 2023The Alan Turing Institute has failed to develop modern AI in the UK
- May 2023A Logic for Expressing Transformers
- Mar 2024“Emergent” abilities in LLMs actually develop gradually and predictably – study
- Jun 2024The illusion of state in state-space models
- Sep 2024Chain of Thought empowers transformers to solve inherently serial problems
- 82
Planting Undetectable Backdoors in Machine Learning Models
Hacker News threads
- 83
AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
Hacker News threads
- Apr 2020AutoML-Zero: Evolving Machine Learning Algorithms from Scratch
- May 2020Evolving Machine Learning Algorithms from Primitive Mathematical Operations
- Apr 2020AutoML-Zero: Evolving Machine Learning Algorithms from Scratch
- Mar 2020AutoML-Zero: Evolving machine learning algorithms from scratch
- Apr 2020Google Engineers Mutate AI to Make Systems Evolve Faster Than We Can Code Them
- May 2020Demo of an OpenAI language model applied to code generation [video]
- Jul 2020AutoML-Zero: Evolving Code That Learns
- 84
Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess
Hacker News threads
- Sep 2020Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess
- Sep 2020Exploring Alternative Rule Sets in Chess with AlphaZero
- Sep 2020Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess
- Dec 2020Ideal Chess – drop chess perfected?
- Aug 2021Fairer Chess: A Reversal of Two Opening Moves in Chess Creates Balance
- Nov 2022Acquisition of chess knowledge in AlphaZero
- Jan 2024I realized chess pieces can be redesigned to be geometric attack directions
- 85
Zero-Shot Text-to-Image Generation
Hacker News threads
- 86
Distributed Deep Learning in Open Collaborations
Hacker News threads
- Jun 2021Distributed Deep Learning in Open Collaborations
- Jun 2021DeDLOC – Distributed Deep Learning in Open Collaborations
- Dec 2023Is there a SETI-like project to train LLM on libgen, scihub and the likes?
- Jan 2024Many AI safety orgs have tried to criminalize currently-existing open-source AI
- Jan 2025Ask HN: Crowdsourced AI Training?
- 87
Learning to summarize from human feedback
Hacker News threads
- Mar 2023Learning to Summarize from Human Feedback
- Sep 2020Learning to Summarize from Human Feedback
- Jan 2023Some Remarks on Large Language Models – Yoav Goldberg
- Mar 2023Microsoft lays off an ethical AI team as it doubles down on OpenAI
- Apr 2023Google DeepMind
- Aug 2025Curious about the training data of OpenAI's new GPT-OSS models? I was too
- 88
Will we run out of data? Limits of LLM scaling based on human-generated data
Hacker News threads
- Aug 2023Will we run out of data to train LLMs?
- Nov 2022We might run out of language data to train ML models soon [pdf]
- Dec 2022An analysis of the limits of scaling datasets in Machine Learning
- Dec 2022Drowning in AI Generated Garbage: the silent war we are fighting
- Dec 2023Dropbox: How to opt out of 3rd party AI partner access to your Dropbox
- Sep 2025Failing to Understand the Exponential, Again
- Sep 2026Nvidia wants to put a watchdog chip next to every AI agent
- 89
GraphCast: Learning skillful medium-range global weather forecasting
Hacker News threads
- Dec 2022End-to-end deep learning methods beat production weather forecast accuracy
- Jan 2023GraphCast: Learning skillful medium-range global weather forecasting
- Aug 2023Ask HN: If we train an LLM with “data” instead of “language” tokens
- Dec 2023Predict the next frame. Results of training a transformer on "visual sentences"
- Dec 2025NOAA deploys new generation of AI-driven global weather models
- Aug 2026DeepMind's WeatherNext model achieves breakthrough forecasting cyclones
- 90
Learned Indexes for a Google-scale Disk-based Database
Hacker News threads
- Oct 2024Learned Indexes for a Google-Scale Disk-Based Database
- Jan 2021PGM Indexes: Learned indexes that match B-tree performance with 83x less space
- Feb 2022Transformer Memory as a Differentiable Search Index
- Jul 2022Ask HN: What are some cool but obscure data structures you know about?
- Jun 2025The probability of a hash collision (2022)
- 91
Locally Typical Sampling
Hacker News threads
- 92
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
- 93
Efficient Training of Language Models to Fill in the Middle
Hacker News threads
- 94
Scaling Instruction-Finetuned Language Models
Hacker News threads
- Dec 2022Scaling Instruction-Finetuned Language Models
- Oct 2022GPT-3 can create both sides of an Interactive Fiction transcript
- Dec 2022Show HN: Web search using a ChatGPT-like model that can cite its sources
- Feb 2023Open source implementation for LLaMA-based ChatGPT
- May 2023Giving GPT “Infinite” Knowledge
- 95
Perceiver: General Perception with Iterative Attention
Hacker News threads
- 96
Towards Understanding Grokking: An Effective Theory of Representation Learning
Hacker News threads
- 97
Large Language Models Encode Clinical Knowledge
Hacker News threads
- Jan 2023Large Language Models Encode Clinical Knowledge
- Dec 2022Large Language Models Encode Clinical Knowledge
- Jan 2023Large Language Models Encode Clinical Knowledge
- Dec 2022Can large language models reason about medical questions?
- Jan 2023GPT-4 could pass Bar Exam, AI researchers say
- Jan 2023Google and DeepMind just launched MedPaLM, a large language model
- Jan 2023An AI robot lawyer was set to argue in court. Real lawyers shut it down
- Mar 2023Capabilities of GPT-4 on Medical Challenge Problems
- Mar 2023Capabilities of GPT-4 on Medical Challenge Problems
- 98
Reading Race: AI Recognises Patient's Racial Identity In Medical Images
Hacker News threads
- Aug 2021AI Recognises Patient's Racial Identity in Medical Images
- Aug 2021Reading Race: AI Recognises Patient's Racial Identity in Medical Images [pdf]
- Aug 2021AI has the worst superpower medical racism
- Sep 2021AI Recognises Race in Medical Images
- Sep 2021AI Recognises Race in Medical Images
- Sep 2021AI Recognises Race in Medical Images
- Dec 2021Training computer vision models on random noise instead of real images
- 99
Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors
Hacker News threads
- Mar 2022Make-a-Scene: Scene-Based Text-to-Image Generation with Human Priors
- Apr 2022Dall-E 2
- Apr 2022Playing with DALL-E 2
- Apr 2022A few things to try with DALL·E
- May 2022My deepfake DALL-E 2 vacation photos passed the Turing Test
- Jul 2022Meta's Make-a-Scene with AI = DALL-E with creative control via simple sketch
- Jul 2022AI image generation: more creative control
- 100
Adversarial Policies Beat Superhuman Go AIs
Hacker News threads
- Dec 2024Adversarial policies beat superhuman Go AIs (2023)
- Nov 2022Adversarial Policies Beat Professional-Level Go AIs
- Feb 2023Man beats machine at Go in human victory over AI
- Feb 202360 Nations agree to regulate AI in the military before it destroys the world
- Apr 2023Ask HN: It is important”, a side effect of Transformers attention?
- Nov 2023In Two Moves, AlphaGo and Lee Sedol Redefined the Future (2016)
Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.