Hacker Papers
- 26
Moshi: a speech-text foundation model for real-time dialogue
Hacker News threads
- 27
The Platonic Representation Hypothesis
Hacker News threads
- May 2024Mutlimodal neural networks converge to a shared statistical model of reality
- Apr 2026The Platonic Representation Hypothesis
- May 2024Show HN: Tarsier – Vision utilities for web interaction agents
- May 2024Ask HN: What is your ChatGPT customization prompt?
- Mar 2025Gödel's theorem debunks the most important AI myth – Roger Penrose [video]
- Jul 2025Ask HN: Will AI models over time converge into the same system?
- Dec 2025The universal weight subspace hypothesis
- Mar 2026Language Model Contains Personality Subnetworks
- Mar 2026I tried Karpathy's Autoresearch on an old research project
- Jul 2026Emily Bender Sets the Record Straight on "Stochastic Parrots"
- 28
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
Hacker News threads
- Oct 2024Understanding the Limitations of Mathematical Reasoning in LLMs
- Oct 2024Cwal: Scripting Engine Without a Language
- Oct 2024Language is not essential for the cognitive processes that underlie thought
- Oct 2024OpenAI builds first chip with Broadcom and TSMC, scales back foundry ambition
- Nov 2024OK, I can partly explain the LLM chess weirdness now
- Dec 2024GPT-5 is behind schedule
- Jan 202530% drop in O1-preview accuracy when Putnam problems are slightly variated
- Jun 2025The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]
- Jul 2026Emily Bender Sets the Record Straight on "Stochastic Parrots"
- 29
Deliberative Alignment: Reasoning Enables Safer Language Models
Hacker News threads
- 30
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Hacker News threads
- Apr 2024OpenAI: Training LLMs to Prioritize Privileged Instructions
- Apr 2024The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
- Apr 2024The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
- Aug 2024Crafting formulas: Lambdas all the way down
- May 2025GitHub MCP exploited: Accessing private repositories via MCP
- Jun 2026A Theory of Why Prompt Injection Works
- 31
DeepSeek-V3 Technical Report
Hacker News threads
- Mar 2025DeepSeek-V3 Technical Report
- Jan 2025DeepSeek-V3 Technical Report
- Jan 2025A path to O1 open source
- Jan 2025Ask HN: Confused about how DeepSeek hurts Nvidia
- Jan 2025Why DeepSeek had to be open source
- Feb 2025Step-Video-T2V: The Practice, Challenges, and Future of Video Foundation Model
- May 2025DeepSeek’s founder is threatening US dominance in AI race
- Feb 2026GLM-5: From Vibe Coding to Agentic Engineering
- Mar 2026Mamba-3
- Jun 2026Two Qwen3 models on one DGX Spark: the residency math
- 32
Reinforcement Learning: An Overview
Hacker News threads
- Feb 2025Reinforcement Learning: An Overview
- Dec 2024Reinforcement Learning: An Overview
- Feb 2025RLHF Book
- Mar 2025Mathematical Foundations of Reinforcement Learning
- Mar 2025A (Long) Peek into Reinforcement Learning
- Nov 2025CS234: Reinforcement Learning Winter 2025
- Jun 2026The 90-year-old idea behind JEPA models: Canonical Correlation Analysis
- 33
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Hacker News threads
- Jan 2025DeepSeek-V2: A Strong, Economical, and Efficient MOE Language Model
- Jan 2025DeepSeek's multi-head latent attention and other KV cache tricks
- Apr 2025Xiaomi MiMo Reasoning Model
- May 2025Attention Wasn't All We Needed
- Dec 2025Zebra-Llama – Towards efficient hybrid models
- Dec 2025Google Titans architecture, helping AI have long-term memory
- Jun 2026How LLMs Work
- 34
Grothendieck's use of equality
Hacker News threads
- 35
People cannot distinguish GPT-4 from a human in a Turing test
Hacker News threads
- May 2024People cannot distinguish GPT-4 from a human in a Turing test
- Jun 2024People cannot distinguish GPT-4 from a human in a Turing test
- Aug 2024Does Reasoning Emerge? Probabilities of Causation in Large Language Models
- Dec 2024GPT-5 is behind schedule
- Jan 2025Show HN: Killed by LLM – I catalogued AI benchmarks we thought would last years
- Feb 2025Modern-Day Oracles or Bullshit Machines? How to thrive in a ChatGPT world
- Apr 2025UCSD: Large Language Models Pass the Turing Test
- Oct 2025A definition of AGI
- Feb 2026Frontier AI agents violate ethical constraints 30–50% of time, pressured by KPIs
- May 2026Dear Richard Dawkins
- 36
Superhuman performance of a large language model on the reasoning tasks of a physician
Hacker News threads
- May 2025Superhuman performance of an LLM on the reasoning tasks of a physician
- Dec 2024Superhuman performance of an LLM on the reasoning tasks of a physician
- Jan 2025Superhuman performance of an LLM on the reasoning tasks of a physician
- Jan 2025Things we learned about LLMs in 2024
- Jan 2025Stargate Project: SoftBank, OpenAI, Oracle, MGX to build data centers
- May 2025The ‘white-collar bloodbath’ is all part of the AI hype machine
- May 2026OpenAI's o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors
- 37
Titans: Learning to Memorize at Test Time
Hacker News threads
- Jan 2025Titans: Learning to Memorize at Test Time
- Jan 2025Titans: Learning to Memorize at Test Time
- Jan 2025Titans: Learning to Memorize at Test Time
- Jan 2025Coming soon: PhD-level super-agents
- Jan 2025Qwen2.5-1M: Deploy your own Qwen with context length up to 1M tokens
- Feb 2025Google Titans Model Explained: The Future of Memory-Driven AI Architectures
- Feb 2025Google Titans Model Explained: The Future of Memory-Driven AI Architectures
- Dec 2025Google Titans architecture, helping AI have long-term memory
- Dec 2025The dawn of a world simulator
- Mar 2026Yann LeCun's AI startup raises $1B in Europe's largest ever seed round
- Apr 2026Show HN: AI memory with biological decay (52% recall)
- 38
Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens
Hacker News threads
- May 2024Infini-Gram: Scaling unbounded n-gram language models to a trillion tokens
- Feb 2024Infini-Gram: Scaling Unbounded N-Gram Language Models to a Trillion Tokens
- Feb 2024Infini-Gram: Scaling unbounded n-gram language models to a trillion tokens
- Feb 2024Markov Chains are the Original Language Models
- Jun 2024Transformers Represent Belief State Geometry in Their Residual Stream
- Nov 2025A new Google model is nearly perfect on automated handwriting recognition
- Nov 2025Ask HN: How are Markov chains so different from tiny LLMs?
- Nov 2025Ask HN: How are Markov chains so different from tiny LLMs?
- Apr 2026Soul Player C64 – A real transformer running on a 1 MHz Commodore 64
- 39
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Hacker News threads
- May 2024Gemini 1.5: Multimodal understanding across tokens of context
- Mar 2024Google's Gemini 1.5 Pro whitepaper
- Mar 2024Gemini 1.5: Unlocking multimodal understanding across tokens of context
- Apr 2024Hello OLMo: A truly open LLM
- Apr 2024Can Gemini 1.5 read all the Harry Potter books at once?
- May 2024Ask HN: Disillusioned after AI?
- Jan 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
- Mar 2026Yann LeCun's AI startup raises $1B in Europe's largest ever seed round
- 40
Amortized Planning with Large-Scale Transformers: A Case Study on Chess
Hacker News threads
- Feb 2024Grandmaster-Level Chess Without Search
- Feb 2024Grandmaster-Level Chess Without Search
- Feb 2024Grand-Master Level Chess Without Search: Modeling Choices and Their Implications
- Apr 2024EURISKO Lives
- Sep 2024Ilya Sutskever's SSI Inc raises $1B
- Oct 2024Grandmaster-level chess without search
- Nov 2024Something weird is happening with LLMs and Chess
- Nov 2024Something weird is happening with LLMs and chess
- Mar 2025Ask HN: Any insider takes on Yann LeCun's push against current architectures?
- Mar 2026Based on its own charter, OpenAI should surrender the race
- 41
Frontier AI systems have surpassed the self-replicating red line
Hacker News threads
- Feb 2025Frontier AI systems have surpassed the self-replicating red line
- Feb 2025Frontier AI systems have surpassed the self-replicating red line
- Jan 2025Self-Replicating AI (lab experiments)
- Jan 2025Emerging reasoning with reinforcement learning
- May 2025Claude Opus 4 turns to blackmail when engineers try to take it offline
- Mar 2026Artificial-life: A simple (300 lines of code) reproduction of Computational Life
- 42
Alignment faking in large language models
Hacker News threads
- Dec 2024AIs Will Increasingly Fake Alignment
- Feb 2025Efficient Reasoning with Hidden Thinking
- Feb 2025Scaling up test-time compute with latent reasoning: A recurrent depth approach
- Aug 2025Is chain-of-thought AI reasoning a mirage?
- Feb 2026An AI Agent Published a Hit Piece on Me – The Operator Came Forward
- Mar 2026Sarvam 105B, the first competitive Indian open source LLM
- 43
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Hacker News threads
- May 2024No "Zero-Shot" Without Exponential Data
- Apr 2024No "Zero-Shot" Without Exponential Data
- Apr 2024No "Zero-Shot" Without Exponential Data
- May 2024Geoffrey Hinton "godfather of AI" says that AI will surpass human intelligence
- Jun 2024Mathematical Optimization for Cargo Ships
- Jun 2024OpenAI and Apple Announce Partnership
- Jun 2024Ask HN: When will we hit a limit on LLM performance?
- Jul 2024Vision language models are blind
- Jul 2024Ask HN: Are there videos of people using AI for non-trivial coding?
- Nov 2024OpenAI, Google and Anthropic are struggling to build more advanced AI
- Feb 2026(AI) Slop Terrifies Me
- 44
Genie: Generative Interactive Environments
Hacker News threads
- Feb 2024Genie: Generative Interactive Environments
- Feb 2024Genie: Generative Interactive Environments
- Feb 2024Genie: Generative Interactive Environments
- Feb 2024Genie: Generative Interactive Environments (DeepMind)
- Dec 2024Genie 2: A large-scale foundation world model
- Jan 2026Project Genie: Experimenting with infinite, interactive worlds
- 45
Bluesky and the AT Protocol: Usable Decentralized Social Media
Hacker News threads
- Feb 2024Bluesky and the AT Protocol: Usable decentralized social media
- Feb 2024Bluesky signups are now open to the public
- Feb 2024Bluesky announces data federation for self hosters
- Feb 2024Bluesky announces data federation for self hosters
- Sep 2024ATProto for distributed system engineers
- Apr 2025Apparently Bluesky has one centralized service, the "relay"
- Jan 2026Publishing on the ATmosphere
- 46
Delving into LLM-assisted writing in biomedical publications through excess vocabulary
Hacker News threads
- Jun 2024Delving into ChatGPT usage in academic writing through excess vocabulary
- Jun 2024Delving into ChatGPT usage in academic writing through excess vocabulary
- Jul 2024Diving into deep learning: Understanding Deep Learning book review [pdf]
- Aug 2024Ask HN: Why does ChatGPT love the word "eager" so much?
- Jan 2026Ask HN: How can you instantly tell something was written by AI?
- 47
Large Concept Models: Language Modeling in a Sentence Representation Space
Hacker News threads
- 48
Optimality of Gerver's Sofa
Hacker News threads
- 49
LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks
Hacker News threads
- 50
Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research
Hacker News threads
Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.