Hacker Papers
- 376
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?
- 377
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
- 378
Large Language Models Cannot Self-Correct Reasoning Yet
Hacker News threads
- Nov 2023LLMs cannot self-correct reasoning yet
- Oct 2023LLMs can't self-correct in reasoning tasks, DeepMind study finds
- Oct 2023GPT-4 Understands
- Apr 2024The question that no LLM can answer and why it is important
- Aug 2024OpenDevin: An Open Platform for AI Software Developers as Generalist Agents
- Mar 2025Show HN: We made an MCP server so Cursor can debug Node.js on its own
- Aug 2026Dutch lawyer fined €2,300 for using AI-hallucinated citation
- 379
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)
- 380
Were RNNs All We Needed?
Hacker News threads
- 381
Deep Learning is Not So Mysterious or Different
Hacker News threads
- Mar 2025Deep Learning Is Not So Mysterious or Different
- Aug 2026Deep Learning Is Not So Mysterious or Different
- Mar 2025Deep Learning Is Not So Mysterious or Different
- Apr 2025Are polynomial features the root of all evil? (2024)
- Aug 2025Do we understand how neural networks work?
- Apr 2026There Will Be a Scientific Theory of Deep Learning
- May 2026A Theory of Deep Learning
- Sep 2026Transformers Explained Visually
- 382
More Agents Is All You Need
Hacker News threads
- Apr 2024More Agents Is All You Need: LLMs performance scales with the number of agents
- Feb 2024More Agents Is All You Need
- Feb 2024More Agents Is All You Need
- Mar 2024Claude 3 beats GPT-4 on Aider's code editing benchmark
- Apr 2024Storm: LLM system that researches a topic and generates full-length wiki article
- Aug 2024AI agents but they're working in big tech
- Sep 2024Learning to Reason with LLMs
- Jan 2025Agents Are Not Enough
- 383
One Glitch to Rule Them All: Fault Injection Attacks Against AMD's Secure Encrypted Virtualization
Hacker News threads
- Aug 2021Fault Injection Attacks Against AMD's Secure Encrypted Virtualization
- Apr 2022Intel deprecates SGX on Core series processors
- Aug 2023AMD Inception Mitigations Can Lower Performance of CPUs by Up to 54%
- Sep 2023Mashing Enter to bypass full disk encryption with TPM, Clevis dracut and systemd
- May 2025Launch HN: Tinfoil (YC X25): Verifiable Privacy for Cloud AI
- Aug 2025A privacy VPN you can verify
- 384
Polynomial Regression As an Alternative to Neural Nets
Hacker News threads
- Jun 2018Polynomial Regression as an Alternative to Neural Nets
- Jun 2018Polynomial Regression as an Alternative to Neural Nets
- Sep 2019NNs are in fact essentially polynomial regression models
- Aug 2019Neural Networks Are Essentially Polynomial Regression
- Aug 2020Differentiable Control Problems
- Oct 2020Why deep learning works even though it shouldn’t
- May 2021Complexity is a source of income in open source ecosystems (2019)
- May 2026A polynomial autoencoder beats PCA on transformer embeddings
- 385
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?
- 386
A Conflict-Free Replicated JSON Datatype
Hacker News threads
- Aug 2016A Conflict-Free Replicated JSON Datatype
- Aug 2016A Conflict-Free Replicated JSON Datatype
- Feb 2018Automerge: JSON-like data structure for building collaborative apps
- May 2018Algorithms Behind Modern Storage Systems
- May 2019Local-first software: You own your data, in spite of the cloud
- Dec 2020Cerulean: Experimental micro-blogging app for Matrix
- Jul 2022Ask HN: What are some cool but obscure data structures you know about?
- 387
A Fast, Minimal Memory, Consistent Hash Algorithm
Hacker News threads
- Mar 2015A Fast, Minimal Memory, Consistent Hash Algorithm
- Aug 2014A Fast, Minimal Memory, Consistent Hash Algorithm
- Mar 2019A Fast, Minimal Memory, Consistent Hash Algorithm (2014)
- Jun 2017When Simple Wins: Power of 2 Load Balancing
- Oct 2021Consistent Hashing for Dummies
- Mar 2022S2: Computational geometry and spatial indexing on the sphere
- May 2024Overflow in consistent hashing (2018)
- Sep 2026Saving another 100TB of RAM
- 388
Tetris is Hard, Even to Approximate
Hacker News threads
- 389
Harnessing the Universal Geometry of Embeddings
Hacker News threads
- May 2025Harnessing the Universal Geometry of Embeddings
- Sep 2026Harnessing the Universal Geometry of Embeddings
- May 2025Text Embeddings are All Alike
- Dec 2025The universal weight subspace hypothesis
- Jan 2026Moltbook
- Mar 2026
- Jul 2026Emily Bender Sets the Record Straight on "Stochastic Parrots"
- Aug 2026Models Are Getting Dumber on Purpose
- 390
Why AI is Harder Than We Think
Hacker News threads
- Apr 2021Why AI is harder than we think
- Aug 2023Why AI Is Harder Than We Think (2021) [pdf]
- Jan 2023Why AI Is Harder Than We Think (2021)
- Apr 2021Superintelligence Risk Project: Conclusion
- May 2021Why A.I. Moonshots Miss
- Jan 2023The Expanding Dark Forest and Generative AI
- Jun 2024Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
- Sep 2025Four Fallacies of Modern AI
- 391
The Peter Principle Revisited: A Computational Study
Hacker News threads
- Jun 2018The Peter Principle Revisited: A Computational Study (2009)
- Feb 2011The Peter Principle Revisited: A Computational Study [pdf]
- Jul 2013The Peter Principle
- Jul 2009Why Incompetence Spreads Through Big Organisations
- Nov 2010Google Engineering Management Mistakes
- Apr 2011Jason Fried: Why I Run a Flat Company
- Nov 2017Hotbed of Misinformation
- Dec 2022Steve Jobs Said the Best Managers Never Want to Be Managers
- 392
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
- 393
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Hacker News threads
- Feb 2015Surpassing Human-Level Performance on ImageNet Classification [pdf]
- Feb 2015Surpassing Human-Level Performance on ImageNet Classification
- Feb 2015Batch Normalization: Accelerating Deep Network Training [pdf]
- Dec 2015Microsoft Research wins image recognition competition
- Oct 2016All Tesla Cars Being Produced Now Have Full Self-Driving Hardware
- May 2020Explainable Deep Learning: A Field Guide for the Uninitiated
- Dec 2023Direct initialization of transformers using larger pretrained ones
- 394
Breaking the Warp Barrier: Hyper-Fast Solitons in Einstein-Maxwell-Plasma Theory
Hacker News threads
- Jul 2022Hyper-fast solitons in Einstein-Maxwell-Plasma Theory (2020)
- Mar 2021Breaking the warp barrier for faster-than-light travel
- May 2021Physical Warp Drives
- Sep 2021Why can’t I go faster than the speed of light?
- Jan 2022The horizon problem for faster than light travel
- Mar 2023SETI@home Is in Hibernation
- 395
Learning to Execute
Hacker News threads
- Oct 2014Learning to Execute
- Nov 2014Learning to Execute [pdf]
- Nov 2014Jeff Hawkins on the Limitations of Artificial Neural Networks
- May 2015The Unreasonable Effectiveness of Recurrent Neural Networks
- Jun 2015A Neural Conversational Model [pdf]
- Jul 2016The future is fewer people writing code?
- Jun 2017DeepFix: Fixing Common C Language Errors by Deep Learning
- 396
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Hacker News threads
- Feb 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attention [pdf]
- Oct 2015Neural Artistic Captions
- Mar 2016AlphaGo beats Lee Sedol again in match 2 of 5
- Oct 2016Deepgram – Find Damning Soundbites
- Feb 2017Understanding deep learning requires rethinking generalization
- Feb 2018Asking the Right Questions About AI
- 397
Design Patterns for Securing LLM Agents against Prompt Injections
Hacker News threads
- Aug 2025Design Patterns for Securing LLM Agents Against Prompt Injections
- Jul 2025Design Patterns for Securing LLM Agents Against Prompt Injections
- Aug 2025Design Patterns for Securing LLM Agents Against Prompt Injections
- Jun 2025Design Patterns for Securing LLM Agents Against Prompt Injections
- Jul 2025Supabase MCP can leak your entire SQL database
- Aug 2025My Lethal Trifecta talk at the Bay Area AI Security Meetup
- Sep 2025Launch HN: Slashy (YC S25) – AI that connects to apps and does tasks
- Jul 2026Leaking YouTube Creators Private Videos
- 398
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
- 399
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
- 400
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
Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.