Hacker Papers

1. 51
   

   Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents

   Jenny Zhang et al. · 2025

   Hacker News threads

   • Jun 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
   • May 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
   • May 2025The Darwin Gödel Machine: AI that improves itself by rewriting its own code
   • May 2025The Darwin Gödel Machine: AI that improves itself by rewriting its own code
   • Jun 2025A deep dive into self-improving AI and the Darwin-Gödel Machine
   • Jun 2025AI Improves at Improving Itself Using an Evolutionary Trick
   • Sep 2025Amazon has mostly sat out the AI talent war
   • Apr 2026

   arXiv ↗
2. 52
   

   ATLAS: Learning to Optimally Memorize the Context at Test Time

   Ali Behrouz et al. · 2025

   Hacker News threads

   • May 2025Atlas: Learning to Optimally Memorize the Context at Test Time
   • Dec 2025Google Titans architecture, helping AI have long-term memory
   • Jan 2026The Q, K, V Matrices
   • Apr 2026Show HN: AI memory with biological decay (52% recall)

   arXiv ↗
3. 53
   

   Can We Fix Social Media? Testing Prosocial Interventions using Generative Social Simulation

   Maik Larooij, Petter Törnberg · 2025

   Hacker News threads

   • Aug 2025Can We Fix Social Media? Testing Prosocial Interventions Using Generative Sims
   • Sep 2025Can We Fix Social Media? Prosocial Interventions Using Generative Simulation
   • Aug 2025Testing Prosocial Interventions Using Generative Social Simulation
   • Aug 2025Study: Social media probably can't be fixed
   • Aug 2025Bluesky: Updated Terms and Policies
   • Oct 2025Situated Software – Clay Shirky (2004)
   • Mar 2026Why I'm betting on ATProto (and why you should, too)

   arXiv ↗
4. 54
   

   Large Language Diffusion Models

   Shen Nie et al. · 2025

   Hacker News threads

   • Feb 2025Large Language Diffusion Models
   • Feb 2025Large Language Diffusion Models
   • Feb 2025Diffusion LLM Has Arrived
   • Feb 2025I think Yann Lecun was right about LLMs (but perhaps only by accident)
   • Feb 2025I think Yann Lecun was right about LLMs (but perhaps only by accident)
   • Mar 2025Beyond Diffusion: Inductive Moment Matching
   • Mar 2025Ask HN: Any insider takes on Yann LeCun's push against current architectures?
   • Apr 2025Yann LeCun, Pioneer of AI, Thinks Today's LLM's Are Nearly Obsolete
   • May 2025Mercury: Commercial-scale diffusion language model
   • Feb 2026Consistency diffusion language models: Up to 14x faster, no quality loss

   arXiv ↗
5. 55
   

   Breaking the Sorting Barrier for Directed Single-Source Shortest Paths

   Ran Duan et al. · 2025

   Hacker News threads

   • Aug 2025Breaking the Sorting Barrier for Directed Single-Source Shortest Paths
   • May 2025Breaking the Sorting Barrier for Directed Single-Source Shortest Paths
   • May 2025Breaking the Sorting Barrier for Directed Single-Source Shortest Paths
   • Aug 2025Breaking the sorting barrier for directed single-source shortest paths
   • Oct 2025A New Algorithm Makes It Faster to Find the Shortest Paths
   • Feb 2026Faster Than Dijkstra?
   • Feb 2026Faster Than Dijkstra?
   • Feb 2026C99 implementation of new O(m log^(2/3) n) shortest path algorithm

   arXiv ↗
6. 56
   

   Scalable Chrysopoeia via $(n, 2n)$ Reactions Driven by Deuterium-Tritium Fusion Neutrons

   Adam Rutkowski et al. · 2025

   Hacker News threads

   • Jul 2025Scalable Chrysopoeia via (N,2n) Reactions Driven by Deuterium-Tritium Fusion
   • Aug 2025An Unusual Way to End Up with a Whole Lot of Gold
   • Sep 2025Marathon Fusion claims it can turn mercury into gold while creating clean energy
   • Feb 2026Cells Use 'Bioelectricity' to Coordinate and Make Group Decisions

   arXiv ↗
7. 57
   

   Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples

   Alexandra Souly et al. · 2025

   Hacker News threads

   • Oct 2025Poisoning Attacks on LLMs Require a Near-Constant Number of Poison Samples
   • Oct 2025Beliefs that are true for regular software but false when applied to AI
   • Nov 2025PRC elites voice AI-skepticism
   • Jan 2026LeCun calls Alex Wang inexperienced, predicts more Meta AI employee departure
   • Jan 2026AI industry insiders launch site to poison the data that feeds them

   arXiv ↗
8. 58
   

   Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline

   Yichen Huang, Lin F. Yang · 2025

   Hacker News threads

   • Jul 2025Gemini 2.5 Pro Capable of Winning Gold at IMO 2025
   • Jul 2025Gemini 2.5 Pro Capable of Winning Gold at IMO 2025 with Prompting
   • Jul 2025Gemini 2.5 Pro Capable of Winning Gold at IMO 2025
   • Jul 2025Gemini with Deep Think achieves gold-medal standard at the IMO
   • Aug 2025GPT-5
   • Aug 2025Claim: GPT-5-pro can prove new interesting mathematics
   • Sep 2025DeepMind and OpenAI win gold at ICPC
   • Oct 2025Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR
   • Oct 2025Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR
   • Nov 2025Yann LeCun to depart Meta and launch AI startup focused on 'world models'
   • Jan 20262025: The Year in LLMs

   arXiv ↗
9. 59
   

   Chain of Draft: Thinking Faster by Writing Less

   Silei Xu et al. · 2025

   Hacker News threads

   • Mar 2025Chain of Draft: Thinking Faster by Writing Less
   • Feb 2025Chain of Draft: Thinking Faster by Writing Less
   • Mar 2025Chain of Draft: Thinking Faster by Writing Less
   • Mar 2025Sketch-of-Thought: Efficient LLM Reasoning
   • May 2025Beyond Semantics: Unreasonable Effectiveness of Reasonless Intermediate Tokens
   • Dec 2025Evaluating chain-of-thought monitorability

   arXiv ↗
10. 60
    

    LLMs Get Lost In Multi-Turn Conversation

    Philippe Laban et al. · 2025

    Hacker News threads

    • May 2025LLMs get lost in multi-turn conversation
    • May 2025The unreasonable effectiveness of an LLM agent loop with tool use
    • Jul 2025The new skill in AI is not prompting, it's context engineering
    • Dec 2025The "confident idiot" problem: Why AI needs hard rules, not vibe checks

    arXiv ↗
11. 61
    

    A convex polyhedron without Rupert's property

    Jakob Steininger, Sergey Yurkevich · 2025

    Hacker News threads

    • Aug 2025A convex polyhedron without Rupert's property
    • Aug 2025A convex polyhedron without Rupert's property
    • Oct 2025First convex polyhedron found that can't pass through itself
    • Nov 2025Ask HN: What Are You Working On? (Nov 2025)
    • Dec 2025Noperthedron is not Rupert (can't fit through itself) [video]

    arXiv ↗
12. 62
    

    Optimal Bounds for Open Addressing Without Reordering

    Martin Farach-Colton et al. · 2025

    Hacker News threads

    • May 2025Optimal bounds for open addressed hash tables without reordering
    • Feb 2025Optimal Bounds for Open Addressing Without Reordering
    • Feb 2025Undergraduate shows that searches within hash tables can be much faster
    • Feb 2025Undergraduate shows that searches within hash tables can be much faster
    • Feb 2025Undergraduate shows that searches within hash tables can be much faster
    • Feb 2025Undergraduate shows that searches within hash tables can be much faster
    • Mar 2025Undergraduate Disproves 40-Year-Old Conjecture, Invents New Kind of Hash Table
    • Dec 2025Speeding Up Hash Tables

    arXiv ↗
13. 63
    

    Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents

    Axel Backlund, Lukas Petersson · 2025

    Hacker News threads

    • Apr 2025Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents
    • May 2025Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents
    • May 2025Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents
    • May 2025Professors Staffed a Fake Company with AI Agents, Guess What Happened?
    • May 2025Trading with Claude, and writing your own MCP server
    • Jun 2025Project Vend: Can Claude run a small shop? (And why does that matter?)
    • Jun 2025Project Vend: Can Claude run a small shop? (And why does that matter?)
    • Jul 2025Can Large Language Models Play Text Games Well? (2023)
    • Jul 2025Ask HN: Why haven't we seen AI as opponents in video games?
    • Oct 2025Our LLM-controlled office robot can't pass butter

    arXiv ↗
14. 64
    

    A Comparison of the Cerebras Wafer-Scale Integration Technology with Nvidia GPU-based Systems for Artificial Intelligence

    Yudhishthira Kundu et al. · 2025

    Hacker News threads

    • Mar 2025Cerebras Wafer-Scale Integration vs. Nvidia GPU-Based Systems for AI
    • May 2025Cerebras achieves 2,500T/s on Llama 4 Maverick (400B)
    • Aug 2025In a first, Google has released data on how much energy an AI prompt uses
    • Oct 2025Cerebras systems raises $1.1B Series G
    • Oct 2025Memory access is O(N^[1/3])

    arXiv ↗
15. 65
    

    Hierarchical Reasoning Model

    Guan Wang et al. · 2025

    Hacker News threads

    • Jul 2025Hierarchical Reasoning Model
    • Jul 2025Hierarchical Reasoning Model
    • Jul 2025Hierarchical Reasoning Model
    • Jul 2025A 27M-param model that solves hard Sudoku/mazes where LLMs fail, without CoT
    • Jul 2025New AI architecture delivers 100x faster reasoning with just 1,000 examples
    • Jul 2025Hierarchical Reasoning Model – 1k training samples SoTA reasoning v/s CoT
    • Aug 2025Is chain-of-thought AI reasoning a mirage?
    • Aug 2025From multi-head to latent attention: The evolution of attention mechanisms
    • Oct 2025Less is more: Recursive reasoning with tiny networks

    arXiv ↗
16. 66
    

    SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?

    Samuel Miserendino et al. · 2025

    Hacker News threads

    • Feb 2025SWE-Lancer: a benchmark of freelance software engineering tasks from Upwork
    • Feb 2025SWE-Lancer: Can LLMs Earn $1M from Real-World Freelance Software Engineering?
    • Feb 2025OpenAI Researchers Find That AI Is Unable to Solve Most Coding Problems
    • Feb 2025GPT-4.5
    • Mar 2025Past and Present Futures of User Interface Design
    • May 2025Semantic unit testing: test code without executing it

    arXiv ↗

Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.