Hacker Papers
- 51
Language Models Represent Space and Time
Hacker News threads
- Oct 2023Paper: LLMs have internal world model, and a sense of time and space
- Nov 2023A Coder Considers the Waning Days of the Craft
- Nov 2023Ask HN: Convince me LLMs aren't just autocomplete with lookahead
- Jul 2024ChatGPT Isn't 'Hallucinating'–It's Bullshitting – Scientific American
- Oct 2024Chain-of-thought can hurt performance on tasks where thinking makes humans worse
- Jun 2025The Emperor's New LLM
- 52
Guiding Language Models of Code with Global Context using Monitors
Hacker News threads
- 53
DeWave: Discrete EEG Waves Encoding for Brain Dynamics to Text Translation
Hacker News threads
- Dec 2023BrainGPT Turns Thoughts into Text
- Dec 2023BrainGPT Turns Thoughts into Text
- Dec 2023BrainGPT Turns Thoughts into Text
- Jun 2024Human neuroscience mustn't forget its human dimension
- May 2025Coding without a laptop: Two weeks with AR glasses and Linux on Android
- Aug 2025Scientists shine a laser through a human head
- 54
Towards Understanding Sycophancy in Language Models
Hacker News threads
- Jun 2025Towards Understanding Sycophancy in Language Models
- Oct 2023Towards Understanding Sycophancy in Language Models
- Oct 2023Towards Understanding Sycophancy in Language Models
- Dec 2023GM Dealer Chat Bot Agrees to Sell 2024 Chevy Tahoe for $1
- Mar 2024Google Scholar search: "certainly, here is" -chatgpt -llm
- May 2026No Slop Grenade
- Jun 2026The US lifts its block on Mythos 5
- 55
Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
Hacker News threads
- Feb 2023Getting more than what you've asked for: The Next Stage of Prompt Engineering
- Feb 2023Novel Prompt Injection Threats to Application-Integrated Large Language Models
- Feb 2023Comprehensive Analysis of Prompt Injection Threats to Large Language Models
- Mar 2023Show HN: ChatGPT Plugins are a security nightmare
- Dec 2023Purple Llama by Meta AI
- Mar 2024Prompt injection and jailbreaking are not the same thing
- Oct 2025NIST's DeepSeek "evaluation" is a hit piece
- 56
Resurrecting Recurrent Neural Networks for Long Sequences
Hacker News threads
- 57
The Design Principles of the Elixir Type System
Hacker News threads
- Jun 2026The design principles of the Elixir type system
- Sep 2023The Design Principles of the Elixir Type System
- Oct 2023The Design Principles of the Elixir Type System
- Nov 2023Elixir at Ramp
- May 2024Elixir and Machine Learning in 2024 so far: MLIR, Arrow, structured LLM, etc.
- Jun 2024Elixir 1.17 released: set-theoretic types in patterns, durations, OTP 27
- Nov 2025Why we migrated from Python to Node.js
- 58
DiLoCo: Distributed Low-Communication Training of Language Models
Hacker News threads
- Jul 2024DiLoCo: Distributed Low-Communication Training of Language Models
- Nov 2023DiLoCo: Distributed Low-Communication Training of Language Models
- Nov 2023Distributed Low-Communication Training of Language Models
- Nov 2023Ultra Fast Bert
- Mar 2024Stable Diffusion 3: Research Paper
- Sep 2024Meta AI: "The Future of AI Is Open Source and Decentralized"
- May 2025Intellect-2 Release: The First 32B Model Trained Through Globally Distributed RL
- 59
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
Hacker News threads
- Jun 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
- Jun 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
- Jun 2023Stochastic Parrot
- Apr 2024The question that no LLM can answer and why it is important
- Jul 2024ChatGPT Isn't 'Hallucinating'–It's Bullshitting – Scientific American
- Aug 2025Persona vectors: Monitoring and controlling character traits in language models
- 60
Efficient Memory Management for Large Language Model Serving with PagedAttention
Hacker News threads
- Sep 2023Efficient Memory Management for Large Language Model Serving with PagedAttention
- Apr 2025Efficient Memory Management for Large Language Model Serving with PagedAttention
- Mar 2024LLMs use a surprisingly simple mechanism to retrieve some stored knowledge
- May 2024Gemini Flash
- Jan 2025Qwen2.5-1M: Deploy your own Qwen with context length up to 1M tokens
- Feb 2026Nano-vLLM: How a vLLM-style inference engine works
- 61
Universal and Transferable Adversarial Attacks on Aligned Language Models
Hacker News threads
- Jul 2023Universal and Transferable Adversarial Attacks on LLM
- Jul 2023Universal and Transferable Adversarial Attacks on Aligned Language Models
- Aug 2023Destroy Humanity Tutorial (ChatGPT Jailbreak)
- Dec 2023Data exfiltration from Writer.com with indirect prompt injection
- Jan 2024Attacks on machine learning models
- Aug 2025Prompting by Activation Maximization
- 62
Emergent Representations of Program Semantics in Language Models Trained on Programs
Hacker News threads
- May 2023Evidence of Meaning in Language Models Trained on Programs
- May 2023Evidence of Meaning in Language Models Trained on Programs
- Jun 2023Evidence of Meaning in Large Language Models Trained on Programs
- May 2023Governance of Superintelligence
- Jun 2023The bigger-is-better approach to AI is running out of road
- Aug 2024Markov chains are funnier than LLMs
- Aug 2026If your agent commits a crime, who is responsible?
- 63
Distinct Elements in Streams: An Algorithm for the (Text) Book
Hacker News threads
- May 2024Distinct Elements in Streams: An Algorithm for the (Text) Book∗ [pdf]
- Nov 2023Ask HN: Is Knuth's TAOCP worth the time and effort? (2023)
- May 2024Computer scientists invent an efficient new way to count
- May 2024Computer scientists invent an efficient new way to count
- May 2024Computer scientists invent an efficient new way to count
- May 2024Computer scientists invent an efficient new way to count
- May 2024Computer scientists invent an efficient new way to count
- Feb 2025Undergraduate shows that searches within hash tables can be much faster
- 64
The Impact of AI on Developer Productivity: Evidence from GitHub Copilot
Hacker News threads
- Jul 2025The Impact of AI on Developer Productivity: Evidence from GitHub Copilot (2023)
- Mar 2023The Impact of AI on Developer Productivity: Evidence from GitHub Copilot
- Jun 2024The Impact of AI on Developer Productivity: Evidence from GitHub Copilot
- Jun 2023Measuring the productivity impact of generative AI
- Aug 2025AI promised efficiency. Instead, it's making us work harder
- Aug 2025I tried coding with AI, I became lazy and stupid
- Jan 20262025: The Year in LLMs
- 65
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
Hacker News threads
- 66
Starlink Generation 2 Mini Satellites: Photometric Characterization
Hacker News threads
- 67
Large Language Models as Optimizers
Hacker News threads
- 68
The Poison of Alignment
Hacker News threads
- 69
In-Context Learning Creates Task Vectors
Hacker News threads
- 70
G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
Hacker News threads
- 71
Efficient Guided Generation for Large Language Models
Hacker News threads
- 72
The Curse of Recursion: Training on Generated Data Makes Models Forget
Hacker News threads
- Dec 2024The Curse of Recursion: Training on generated data makes models forget (2023)
- Jun 2023The Curse of Recursion: Training on Generated Data Makes Models Forget
- Jun 2023The Curse of Recursion: Training on Generated Data Makes Models Forget
- Jun 2023Two US lawyers fined for submitting fake court citations from ChatGPT
- Jun 2023The Darwinian argument for worrying about AI
- Jul 2023LLaMA2 isn't “Open Source” – and why it doesn't matter
- Nov 2023Using GPT-4 Vision with Vimium to browse the web
- Jan 2024The Internet Is Full of AI Dogshit
- Feb 2024Generative AI Degrades Online Communities
- Apr 2024Tell HN: We should snapshot a mostly AI output free version of the web
- Jun 2024Gemma 2: Improving Open Language Models at a Practical Size [pdf]
- 73
Reflexion: Language Agents with Verbal Reinforcement Learning
Hacker News threads
- Mar 2023Reflexion: An autonomous agent with dynamic memory and self-reflection
- Mar 2023Reflexion: An autonomous agent with dynamic memory and self-reflection
- Mar 2023Reflexion: An autonomous agent with dynamic memory and self-reflection
- Mar 2023GPT-4 performs significantly worse on coding problems not in its training data
- Mar 2023ChatGPT and Code Interpreter = Magic
- Apr 2023HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends in HuggingFace
- Apr 2023Defamed by ChatGPT: Law professor libeled from whole cloth
- Apr 2023Large Language Models: Scaling Laws and Emergent Properties
- Jul 2023Langchain Is Pointless
- Aug 2023Maccarone: AI-managed code blocks in Python
- Oct 2024Update on Reflection-70B
- 74
Do Black Holes have Singularities?
Hacker News threads
- Dec 2023Roy Kerr: Do Black Holes Have Singularities?
- Feb 2024Relativistic Spaceship
- Feb 2024Brightest and fastest-growing: astronomers identify record-breaking quasar
- Apr 2024Astronomers discover Milky Way’s biggest stellar black hole
- May 2024Three of the oldest stars in the universe found circling the Milky Way
- Jun 2024Einstein and his peers were resistant to black holes
- Jul 2024Cosmic simulation reveals how black holes grow and evolve
- Oct 2024On the Nature of Time
- Mar 2025James Webb Space Telescope reveals that most galaxies rotate clockwise
- 75
LIMA: Less Is More for Alignment
Hacker News threads
- May 2023LIMA: Less Is More for Alignment
- May 2023LIMA: Less Is More for Alignment
- May 2023GPT detectors are biased against non-native English writers
- May 2023How to Finetune GPT Like Large Language Models on a Custom Dataset
- Jun 2023Falcon 40B LLM (which beats Llama) now Apache 2.0
- Jun 2023AI has poisoned its own well
- Sep 2023Large Language Models for Compiler Optimization
- Sep 2023Outperforming LLMs with less training data and smaller model sizes
- Apr 2024Ask HN: Most efficient way to fine-tune an LLM in 2024?
- Oct 2024Zamba2-7B
Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.