Hacker Papers
- 576
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
- 577
On the Paradox of Learning to Reason from Data
Hacker News threads
- Aug 2022On the Paradox of Learning to Reason from Data
- Jun 2024The Paradox of Learning to Reason from Data (2022)
- Jul 2023On the Paradox of Learning to Reason from Data
- Dec 2022Artificial Intelligence Is Stupid and Causal Reasoning Will Not Fix It
- Feb 2023Getty Images v. Stability AI – Complaint
- Mar 2023Understanding ChatGPT
- Mar 2023HN thread 35320870
- Jul 2023PoisonGPT: We hid a lobotomized LLM on Hugging Face to spread fake news
- Sep 2023Provably safe systems: the only path to controllable AGI
- Oct 2024DeepSeek: Advancing theorem proving in LLMs through large-scale synthetic data
- 578
Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
Hacker News threads
- May 2023Attention with Linear Biases (ALiBi)
- May 2023Replit's new Code LLM: Open Source, 77% smaller than Codex, trained in 1 week
- May 2023Anthropic - Introducing 100K Token Context Windows, Around 75,000 Words
- Jul 2023
- Aug 2023Code Llama, an AI tool for coding
- Aug 2023
- Jan 2024ChatGPT for Teams
- Oct 2024Differential Transformer
- 579
A Length-Extrapolatable Transformer
Hacker News threads
- 580
Deep Voice: Real-time Neural Text-to-Speech
Hacker News threads
- 581
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
- 582
Repeat After Me: Transformers are Better than State Space Models at Copying
Hacker News threads
- 583
Scalable MatMul-free Language Modeling
Hacker News threads
- Jun 2024Scalable MatMul-Free Language Modeling
- Jun 2024Scalable MatMul-Free Language Modeling
- Jun 2024Scalable MatMul-Free Language Modeling
- Jun 2024Researchers run high-performing LLM on the energy needed to power a lightbulb
- Jun 2024Researchers run high-performing LLM on the energy needed to power a lightbulb
- Jun 2024Researchers upend AI status quo by eliminating matrix multiplication in LLMs
- Sep 2024Hardware Acceleration of LLMs: A comprehensive survey and comparison
- Oct 2024Addition is All You Need for Energy-efficient Language Models
- 584
Deep Unsupervised Learning using Nonequilibrium Thermodynamics
Hacker News threads
- May 2015Deep Unsupervised Learning Using Nonequilibrium Thermodynamics [pdf]
- Apr 2022Dall-E 2
- Oct 2022The Illustrated Stable Diffusion
- Jan 2023Denoising Diffusion models from first principle in Julia
- Jul 2023Stanford A.I. Courses
- Feb 2024Mamba Explained: The State Space Model Taking On Transformers
- May 2024Diffusion Models
- Sep 2024Physics is unreasonably good at creating new math
- Sep 2024Too much efficiency makes everything worse (2022)
- 585
Paxos vs Raft: Have we reached consensus on distributed consensus?
Hacker News threads
- Apr 2020Paxos vs. Raft: Have we reached consensus on distributed consensus?
- May 2024Paxos vs. Raft: Have we reached consensus on distributed consensus? (2020)
- May 2020In Search of an Understandable Consensus Algorithm (2014) [pdf]
- May 2020In Search of an Understandable Consensus Algorithm (2014) [pdf]
- Oct 2020A Review of Consensus Protocols
- May 2021Ethereum will use around 99.95% less energy post merge
- Jan 2022Paxos
- Aug 2022Why use Paxos instead of Raft?
- Sep 2024Raft: Understandable Distributed Consensus (2014)
- Sep 2024Raft: Understandable Distributed Consensus (2014)
- 586
An Overview on IEEE 802.11bf: WLAN Sensing
Hacker News threads
- 587
Generative Adversarial Networks
Hacker News threads
- May 2023Generative Adversarial Networks
- Nov 2016Generative Adversarial Nets [pdf]
- Jun 2014Does Deep Learning Have Deep Flaws?
- Jan 2017Game Theory Reveals the Future of Deep Learning
- Aug 2017Ask HN: What is your favorite CS paper?
- Jan 2018AI System Sorts News Articles by Whether or Not They Contain Actual Information
- Jun 2020AI vs. AI
- May 2022Apple's director of machine learning resigns due to return to office work
- Nov 2023SDXL Turbo: A Real-Time Text-to-Image Generation Model
- Sep 2024Xkcd 1425 (Tasks) turns ten years old today
- 588
Deep Learning in Neural Networks: An Overview
Hacker News threads
- May 2014Deep learning in neural networks: An overview
- Dec 2023Deep Learning in Neural Networks: An Overview
- Dec 2014Unsupervised Feature Learning and Deep Learning Recommended Readings
- Dec 2014Technical Papers Every Programmer Should Read at Least Twice (2011)
- Sep 2016Artificial Intelligence Software Is Booming, But Why Now?
- Jan 2017AI Pioneer Wants to Build the Renaissance Machine of the Future
- Jul 2018Ernst Dickmanns, a German scientist who developed self-driving cars in the 1980s
- Jun 2019Ask HN: Please suggest review papers in CS topics
- Nov 2023Show HN: Tiny LLMs – Browser-based private AI models for a wide array of tasks
- Sep 2024OpenAI to become for-profit company
- 589
The Grand Illusion: The Myth of Software Portability and Implications for ML Progress
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
- 590
Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions
Hacker News threads
- 591
Dissociating language and thought in large language models
Hacker News threads
- Sep 2024Dissociating language and thought in large language models
- Jan 2023Dissociating language and thought in LLMs: a cognitive perspective
- Feb 2023Dissociating language, thought in large language models: a cognitive perspective
- Feb 2023I had ChatGPT write a Decemberists song
- Feb 2023Theory of Mind May Have Spontaneously Emerged in Large Language Models (2021)
- Apr 2023Why ChatGPT and Bing Chat are so good at making things up
- May 2023Geoffrey Hinton leaves Google and can now speak freely about his AI concern
- Jul 2023A Latent Space Theory for Emergent Abilities in Large Language Models
- Oct 2023Ask HN: Why are current LLMs not considered AGI?
- 592
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Hacker News threads
- Mar 2024Pg_vectorize: Vector search and RAG on Postgres
- Mar 2024Pg_vectorize: Vector search and RAG on Postgres
- Mar 2024Raptor: Recursive Abstractive Processing for Tree-Organized Retrieval
- Mar 2024Show HN: Out-of-the-box text classification models
- May 2024Systematically Improving Your RAG
- May 2024Ask HN: RAG and unstructured data from several docs
- Sep 2024Contextual Retrieval
- Sep 2024Contextual Retrieval
- 593
The Halo Drive: Fuel-Free Relativistic Propulsion of Large Masses via Recycled Boomerang Photons
Hacker News threads
- Mar 2019Fuel-Free Relativistic Propulsion of Large Masses via Recycled Boomerang Photons
- Jan 2023The Halo Drive: Fuel-Free Relativistic Propulsion (2019)
- Aug 2019The “Terrascope”: On the Possibility of Using the Earth as an Atmospheric Lens
- Jun 2023Freeman Dyson: Gravitational Machines
- Sep 2024Biggest ever seen black hole jets; blasting plasma well beyond their own galaxy
- 594
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
- 595
Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
Hacker News threads
- 596
Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
Hacker News threads
- Mar 2024Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
- Mar 2024How Chain-of-Thought Reasoning Helps Neural Networks Compute
- Mar 2024How Chain-of-Thought Reasoning Helps Neural Networks Compute
- Mar 2024Can Demis Hassabis save Google?
- Apr 2024Mixture-of-Depths: Dynamically allocating compute in transformers
- May 2024The "Chain of Thought" Delusions
- Aug 2024OpenAI shows 'Strawberry' to feds, races to launch it
- Sep 2024Learning to Reason with LLMs
- Sep 2024g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains
- 597
Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
Hacker News threads
- 598
Experimental loophole-free violation of a Bell inequality using entangled electron spins separated by 1.3 km
Hacker News threads
- Oct 2015Quantum Theory Experiment Said to Prove ‘Spooky’ Interactions
- Aug 2018Do electrons think? (1949)
- May 2021What did Einstein mean by “spooky action at a distance”?
- May 2021What did Einstein mean by “spooky action at a distance”?
- Sep 2024Breaking Bell's Inequality with Monte Carlo Simulations in Python
- 599
Seven Sketches in Compositionality: An Invitation to Applied Category Theory
Hacker News threads
- Jul 2019Seven Sketches in Compositionality: An Invitation to Applied Category Theory
- Mar 2018Seven Sketches in Compositionality: An Invitation to Applied Category Theory
- May 2018Seven Sketches in Compositionality: An Invitation to Applied Category Theory
- Feb 2019A monad is a monoid in the category of endofunctors, what’s the problem?
- Apr 2019Applied Category Theory
- Jan 2020To Dissect a Mockingbird: A Graphical Notation for the Lambda Calculus (1996)
- Apr 2020Ask HN: What are you learning?
- Feb 2021Ask HN: What mathematical background do I need to understand category theory?
- Apr 2021Category theory is a universal modeling language
- Nov 2022Applied category theory in chemistry, computing, and social networks [pdf]
- Sep 2024The Theory of Topos-Theoretic 'Bridges' – A Conceptual Introduction (2016)
- 600
Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B
Hacker News threads
Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.