Hacker Papers
- 251
Character-Aware Models Improve Visual Text Rendering
Hacker News threads
- Dec 2022Improving Text Rendering in Image Generation Models
- Dec 2022What ChatGPT Can't Do
- Feb 2023Illusion Diffusion: Optical Illusions Using Stable Diffusion
- Apr 2023A Baby GPT
- Apr 2023Stability AI releases DeepFloyd IF, a powerful text-to-image model
- Oct 2023DALL-E 3: Improving image generation with better captions [pdf]
- Mar 2024Ask HN: Why can't image generation models spell?
- 252
The Forward-Forward Algorithm: Some Preliminary Investigations
Hacker News threads
- Jan 2023The Forward-Forward Algorithm, potential alternative to backpropagation
- May 2023The Forward-Forward Algorithm: Some Preliminary Investigations (2022)
- Jan 2023Deep Learning Pioneer Geoffrey Hinton Publishes New Deep Learning Algorithm
- Jun 2023MeZO: Fine-Tuning Language Models with Just Forward Passes
- Jun 2023Geoffrey Hinton: “We're toast. This is the actual end of history”
- Apr 2024Storm: LLM system that researches a topic and generates full-length wiki article
- Jul 2024Training of Physical Neural Networks
- Jan 2025Antiqua et Nova: Note on the relationship between AI and human intelligence
- 253
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
Hacker News threads
- Nov 2016MXNet – Deep Learning Framework of Choice at AWS
- Mar 2017Why is so much memory needed for deep neural networks?
- Jun 2017Facebook Trains ImageNet in 1 Hour
- Dec 2017An Interview with an Anonymous Data Scientist (2016)
- Dec 2017Mathematics of Deep Learning [pdf]
- Nov 2025Backpropagation is a leaky abstraction (2016)
- 254
Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions
Hacker News threads
- Aug 2021An empirical cybersecurity evaluation of GitHub Copilot's code contributions
- Sep 2021GitHub Copilot Generated Insecure Code in 40% of Circumstances During Experiment
- Sep 2021GitHub Copilot Generated Insecure Code in 40% of Circumstances During Experiment
- Oct 2021GitHub Copilot available for JetBrains and Neovim
- Jun 2022Papers on GitHub Copilot, copyright law, and ownership for AI-generated code
- Dec 2022Study finds AI assistants help developers produce code likely to be buggy
- Jan 2023It's Plausible, but Is It True?
- 255
Deep Speech: Scaling up end-to-end speech recognition
Hacker News threads
- Dec 2014DeepSpeech: Scaling up end-to-end speech recognition
- Feb 2015Deep Speech: Scaling up end-to-end speech recognition
- Dec 2014DeepSpeech: Scaling up end-to-end speech recognition [pdf]
- Jun 2015What's Wrong with Deep Learning?
- Oct 2015How Baidu is improving Mandarin voice recognition with deep learning
- Feb 2017How to Train Baidu's Deepspeech Model with Kur
- Dec 2017A TensorFlow implementation of Baidu's DeepSpeech architecture
- Aug 2021Mozilla Common Voice Adds 16 New Languages and 4,600 New Hours of Speech
- 256
Scalable Extraction of Training Data from (Production) Language Models
Hacker News threads
- Dec 2023Scalable Extraction of Training Data from (Production) Language Models
- Nov 2023Extracting Training Data from LLMs
- Nov 2023Scalable Extraction of Training Data from (Production) Language Models
- Dec 2023Sorry, but a new prompt for GPT-4 is not a paper
- Jan 2024Nightshade: An offensive tool for artists against AI art generators
- Feb 2024Beyond self-attention: How a small language model predicts the next token
- Oct 2025What GPT-OSS leaks about OpenAI's training data
- Nov 2025The current state of the theory that GPL propagates to AI models
- 257
One Model To Learn Them All
Hacker News threads
- Jun 2017One Model to Learn Them All
- Oct 2024One Model to Learn Them All
- Jul 2017One Model to Learn Them All
- Jun 2017Google advances AI with ‘one model to learn them all’
- Jul 2017The future of deep learning
- Nov 2017Low Hanging Fruit of Programming Language Design
- Feb 2018The Shallowness of Google Translate
- Mar 2019Yann LeCun, Geoffrey Hinton and Yoshua Bengio win Turing Award
- 258
Deep Learning for Symbolic Mathematics
Hacker News threads
- Dec 2019Deep Learning for Symbolic Mathematics
- Dec 2019Deep Learning for Symbolic Mathematics – NN that can do advanced math [Facebook]
- Jan 2020Deep Learning for Symbolic Mathematics
- Mar 2020Differential Equations with Transformers: Deep Learning for Symbolic Math
- May 2020Symbolic mathematics finally yields to neural networks
- May 2020Symbolic mathematics finally yields to neural networks
- Aug 2020Natural language benchmarks don’t measure AI models’ general knowledge well
- May 2022Learning to think critically about machine learning
- Mar 2023The Age of AI has begun
- 259
Wasserstein GAN
Hacker News threads
- Jan 2017Wasserstein GAN
- Feb 2017Wasserstein GAN
- May 2017Sorting Two Tons of Lego, the Software Side
- Aug 2017Do I really have to cite an arXiv paper?
- Apr 2018Building a Content-Based Search Engine IV: Earth Mover's Distance
- Dec 2018Machine learning is not just glorified statistics
- Apr 2019Open Questions about Generative Adversarial Networks
- 260
Are Transformers Effective for Time Series Forecasting?
Hacker News threads
- Jan 2024Are Transformers Effective for Time Series Forecasting?
- Apr 2023From Deep to Long Learning
- Feb 2024A decoder-only foundation model for time-series forecasting
- Jul 2024XLSTMTime: Long-Term Time Series Forecasting with xLSTM
- Jun 2025Time Series Forecasting with Graph Transformers
- Dec 2025The Illustrated Transformer
- 261
A Practical Deep Learning-Based Acoustic Side Channel Attack on Keyboards
Hacker News threads
- Jan 2026Acoustic Side Channel Attack on Keyboards (2023)
- Aug 2023A Practical Deep Learning-Based Acoustic Side Channel Attack on Keyboards
- Aug 2023A Practical Deep Learning-Based Acoustic Side Channel Attack on Keyboards
- Aug 2023Write your passwords down (2010)
- Oct 2023OpenSSH 9.5 released with keystroke timing obfuscation
- Dec 2023Scary AI recognizes passwords by the sound of your typing
- Nov 2024Malware can turn off webcam LED and record video, demonstrated on ThinkPad X230
- Mar 2026Ubuntu 26.04 Ends 46 Years of Silent sudo Passwords
- 262
Backprop as Functor: A compositional perspective on supervised learning
Hacker News threads
- Dec 2018Backprop as Functor: A compositional perspective on supervised learning [pdf]
- Feb 2018NLP concepts with spaCy tutorial
- Mar 2018Applied Category Theory
- Apr 2019Applied Category Theory
- Sep 2019The beauty of functional languages in deep learning – Clojure and Haskell
- Apr 2021Predictive coding has been unified with backpropagation
- 263
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
Hacker News threads
- Oct 2023SWE-Bench: Can Language Models Resolve Real-World GitHub Issues?
- Feb 2024SWE-BENCH: Can language models resolve real-world GitHub issues?
- Jan 2024Researchers say generative AI isn't replacing devs any time soon
- Sep 2025Top model scores may be skewed by Git history leaks in SWE-bench
- Dec 2025Django: what’s new in 6.0
- Mar 2026Ask HN: Does code style matter much anymore?
- Oct 2026Agents don't need memory, they need documentation
- 264
Image Super-Resolution Using Deep Convolutional Networks
Hacker News threads
- Aug 2015Image Scaling using Deep Convolutional Neural Networks
- Oct 2016Neural Enhance – Super Resolution for images using deep learning
- Nov 2016RAISR Sharp Images with Machine Learning
- Nov 2016RAISR Sharp Images with Machine Learning
- Jan 2017With Google's RAISR, images can be up to 75% smaller without losing detail
- Feb 2017The Convex Geometry of Inverse Problems [video]
- 265
Memory Networks
Hacker News threads
- Nov 2014Memory Networks
- Feb 2015Facebook Memory Networks
- Mar 2015Memory Network [pdf]
- Mar 2015Facebook's Memory Networks Demo
- Mar 2015By 2029 no computer or “machine intelligence” will have passed the Turing Test
- May 2015Are There Deep Reasons Underlying the Pathologies of Deep Learning Algorithms? [pdf]
- Jul 2015FANN.js – Fast Artificial Neural Network Compiled with Emscripten
- Oct 2016Hybrid computing using a neural network with dynamic external memory
- Oct 2025A History of Large Language Models
- 266
Probing Neural Network Comprehension of Natural Language Arguments
Hacker News threads
- Jul 2019Probing Neural Network Comprehension of Natural Language Arguments
- Jul 2019BERT's success due to 'spurious statistical cues'
- Jul 2019Probing Neural Network Comprehension of Natural Language Arguments
- Jul 2019A Worrying Analysis of Recent Neural Recommendation Approaches
- Aug 2019AI startup claims to automate app making but actually just uses humans
- Nov 2019Douglas Hofstadter: The Shallowness of Google Translate (2018)
- Dec 2023Ask HN: What is the current state of "logical" AI?
- May 2024How does AI impact my job as a programmer?
- 267
Solving Quantitative Reasoning Problems with Language Models
Hacker News threads
- Sep 2022Solving Quantitative Reasoning Problems with Language Models
- Oct 2022AI language models are struggling to “get” math
- Dec 2022Building a Virtual Machine Inside ChatGPT
- Feb 2023To Build Truly Intelligent Machines, Teach Them Cause and Effect
- Nov 2023Sam Altman's ouster was precipitated by letter to board about AI breakthrough
- Jan 2025Berkeley Researchers Replicate DeepSeek R1's Core Tech for Just $30: A Small Mod
- 268
The importance of quantum decoherence in brain processes
Hacker News threads
- Sep 2017The importance of quantum decoherence in brain processes (1999)
- Jan 2018The importance of quantum decoherence in brain processes (1999)
- Jan 2019The importance of quantum decoherence in brain processes – Max Tegmark (1999)
- Mar 2012Gödel's Incompleteness Theorem explained
- Feb 2013The Brain is Not Computable
- Aug 2013Simulating 1 second of real brain activity takes 40 minutes and 83K processors
- Jun 2018I'm Scott Aaronson, quantum computing/computational complexity researcher. AMA
- Nov 2018The Strong Free Will Theorem (2009) [pdf]
- 269
Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
Hacker News threads
- Mar 2021Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in NLI (2019)
- Jul 2019Microsoft is investing $1B in OpenAI
- Jul 2020Why GPT-3 Matters
- Aug 2021Machine learning won't solve natural language understanding
- Oct 2021Dense Vectors: Capturing Meaning with Code
- Dec 2021A cartel of influential datasets are dominating machine learning research
- 270
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
Hacker News threads
- Sep 2019GPT-2 is not as dangerous as OpenAI thought it might be
- Nov 2019A.I. and the Future of Cheating
- Dec 2019The dark ages of AI: A panel discussion at AAAI-84 (1985)
- Aug 2020Deep learning job postings have collapsed in the past six months
- Jan 2023ChatRWKV, like ChatGPT but powered by the RWKV (RNN-based, open) language model
- 271
Denoising Diffusion Probabilistic Models
Hacker News threads
- 272
Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models
Hacker News threads
- Dec 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion
- Dec 2022Investigating Data Replication in Diffusion Models
- Dec 2022Diffusion Art or Digital Forgery? Data Replication in Diffusion Models
- Dec 2022GPT3/DALL-E2 in Discord, chat like ChatGPT, generate images, and more
- Jan 2023Lawsuit challenging Stable Diffusion filed against DeviantArt & others
- Jan 2023Lawsuit challenging Stable Diffusion filed against DeviantArt & others
- Jan 2023Stable Diffusion Frivolous Litigation
- Jan 2023An IP Attorney’s Reading of the Stable Diffusion Class Action Lawsuit
- Feb 2023Stable Diffusion found to emit some images from training at generation time
- Feb 2023Stable Attribution
- Jul 2024Brazil data regulator bans Meta from mining data to train AI models
- 273
Stealing Machine Learning Models via Prediction APIs
Hacker News threads
- Sep 2016Stealing Machine Learning Models via Prediction APIs
- Jan 2019Stealing Machine Learning Models via Prediction APIs (2016) [pdf]
- Apr 2018Stealing Machine Learning Models via Prediction APIs (2016)
- Dec 2016How to Steal an AI (reverse engineer machine-learning)
- Dec 2016Stealing Machine Learning Models via Prediction APIs
- Jan 2017Amazon AI
- Mar 2017Cloud Video Intelligence API
- Mar 2017Ask HN: What does your production machine learning pipeline look like?
- Mar 2017I reverse-engineered a $500M Artificial Intelligence company in one week
- Jun 2018Attacks against machine learning – an overview
- 274
A Style-Based Generator Architecture for Generative Adversarial Networks
Hacker News threads
- Dec 2018A Style-Based Generator Architecture for Generative Adversarial Networks [pdf]
- Dec 2018Artificial Intelligence Creates Realistic Pictures of People
- Feb 2019Nvidias recent face generation deep neural network (keep refreshing)
- Feb 2019This person does not exist
- Feb 2019This person does not exist
- Feb 2019Show HN: Fake Profile Picture Generator
- Feb 2019This Waifu Does Not Exist
- Jun 2021Alias-Free GAN
- Oct 2021Greater than 99% consensus on human caused climate change in the literature
- 275
Getting from Generative AI to Trustworthy AI: What LLMs might learn from Cyc
Hacker News threads
- Aug 2023Getting from Generative AI to Trustworthy AI: What LLMs Might Learn from Cyc
- Sep 2023Getting from Generative AI to Trustworthy AI: What LLMs Might Learn from Cyc
- Aug 2023Getting from Generative AI to Trustworthy AI: What LLMs Might Learn from Cyc
- Sep 2023Doug Lenat has died
- Sep 2023Recursively Summarizing Enables Long-Term Dialogue Memory in LLMs
- Sep 2023Lenat and Cyc
- Jun 2024ARC Prize – a $1M+ competition towards open AGI progress
- Nov 2024LLMs have reached a point of diminishing returns
- Apr 2025Obituary for Cyc
Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.