‘newest links’ directory
- See Also
- Gwern
- “Tea: Steeped or Shaken?”, Astra et al 2026
- “Lighthaven Flood Risk”, Astra et al 2026
- “Why Shakespeare Drew Crowds”, Astra et al 2026
- “She’s She, and I’m I”, Gwern & Claude-5.1-Fable 2026
- “Frutiger Ero”, Gwern & Pro 2026
- “LLM Time Travel Visualization”, Gwern 2026
- “Sleepcat Purrkit”, Gwern et al 2026
- “The Repugnant Conclusion”, Gwern & 2 2026
- “Lean Software Scaling Laws”, Gwern 2025
- “Face Recognition Training App”, Gwern 2026
- “Sand, Rain, Wood”, Gemini-3.1-pro-preview et al 2026
- “𝑃𝑒𝑟𝑖𝑠𝘩𝑒𝑑 𝑃𝑎𝑟𝑎𝑑𝑖𝑠𝑒 Graveyard”, Gwern 2023
- “Chapter 6, Mime Molting: What to Expect”, Claude-4.8-opus et al 2026
- Links
- “How Curl Was Accidentally Turing-Complete for 9 Months”
- “Tallis, Spem in Alium © (40-Voice Motet)”
- “Introducing Gemini 4 Carbon”
- “Exposing AdFection: How Discover-Tech Turned Targeted Ads Into a Pipeline for Zero-Click Mercenary Spyware”
- “Vowz Bar Recommended Cocktails Menu”, Bar 2026
- “Binding Atlas”
- “Complete Finite Simple Group Classification Proof in Lean”, Axiom 2026
- “Concerning Behavior from a Popular Open-Weight AI Model: Inside a Closed Testing Sandbox Managed by Cohere, One of Alibaba's Newest Qwen3.8 Models Attempted to Push a Diagnostic File toward a Remote Storage Container Situated in Beijing. Just prior to Taking This Action, the Model's Reasoning Stream Had Explicitly Stated That Zero Tools Would Be Triggered”, Cohere 2026
- “Interactions Are Generally Not Important in Social Science”, Kirkegaard 2026
- “Interactions Are Still Not Important: Not in Medical Data Either”, Kirkegaard 2026
- “Neuron Persona Library”
- “Fermi Poker”
- “Robustified ANNs Reveal Wormholes Between Human Category Percepts”, Gaziv et al 2023
- “Attention Is Not What You Need”, Chong 2025
- “How to Run Turing-Complete Malware in PyTorch’s Backward Pass”
- “Spending 10 Months Building the Most Human-Like Chess Bot”, mbuffett 2026
- “
lgit: Source Control for the AI Era”, Brenner 2026 - “Make or Buy: The Economics of Decision Models”
- “Doing Business In Japan”, McKenzie 2014
- “How Does Claude-5.1-Fable Hide Messages in Images?”
- “Every AI Model Has the Same ‘Controversial’ Take on Humans”
- “How Far Will AI Assistants Go for a Refund They Can’t Get? Spamming the Government, Using a Sick Mother As Leverage and Threatening the Small Claims Court”, Glynn-Henley 2026
- “Shichiri Beach in Sagami Province (36 Views of Mount Fuji)”
- “Investing in the Public Benefit”, Anthropic 2026
- “Aerolamp: Far UV 222nm Lamp—Germicidal Far UVC Light Room Sanitizer”, Aerolamp 2026
- “Diffusion at Scale: Introducing Mercury 3”
- “The Predominance of ‘7’ and the Apparent Spontaneity of Numerical Choices”, Kubovy & Psotka 1976
- “AI Models Can Provably Hide Arbitrary Capabilities”, Draguns et al 2026
- “The Role of Personality and Intelligence in Assortative Mating”, Escorial et al 2012
- “Quantum-Computable One-Way Functions without One-Way Functions”, Kretschmer et al 2024
- “Training Language Models via Neural Cellular Automata”, Lee et al 2026
- “Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors”, Dubiński et al 2026
- “A Founder Population Reveals Genetic Variation With Major Effect on Serious Mental Illness”, Gerdes et al 2026
- “Zen Puzzle Garden Is NP-Complete”, Houston et al 2011
- “Why Backdooring Neural Networks Is so Easy?”, Seddik & Seddik 2026
- “Toward Robust Non-Transferable Learning: A Survey and Benchmark”, Hong et al 2025
- “‘As a Language Model…’: Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It”, Maczan 2026
- “Soft Contamination Means Benchmarks Test Shallow Generalization”, Spiesberger et al 2026
- “Generative AI Floods and Dilutes the Market for Books”, Chakrabarty et al 2026
- “DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale”, Huang et al 2026
- “ECO: An LLM-Driven Efficient Code Optimizer for Warehouse Scale Computers”, Lin et al 2025
- “Adversarial Poetry As a Universal Single-Turn Jailbreak Mechanism in Large Language Models”, Bisconti et al 2025
- “Stealing Reasoning Traces from Proprietary LLM APIs”, Panfilov et al 2026
- “Souper-Model: How Simple Arithmetic Unlocks State-Of-The-Art LLM Performance”, Maiti et al 2025
- “Benchmarks for Detecting Measurement Tampering”, Roger et al 2023
- “Compression Is All You Need: Modeling Mathematics”, Aksenov et al 2026
- “Score Centering Stabilizes Off-Policy Reinforcement Learning”, Marek & Ryabinin 2026
- “Two Parallel Lineage-Committed Progenitors Contribute to the Developing Brain”, Dundes et al 2025
- “Likelihood-Free Hypothesis Testing”, Gerber & Polyanskiy 2022
- “Digital Red Queen: Adversarial Program Evolution in Core War With LLMs”, Kumar et al 2026
- “FlashAccel: Leveraging High-Bandwidth Flash (HBF) for High-Throughput LLM Inference”, Wang et al 2026
- “RoboTTT: Context Scaling for Robot Policies”, Jiang et al 2026
- “Crossing the Streams: SSH Plaintext Recovery via a Common Compression Context in Multiplexed Channels”, Bäumer & Brinkmann 2026
- “How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks”, Ansari et al 2026
- “Brain Drain or Brain Gain? Effects of High-Skilled International Emigration on Origin Countries”, Batista et al 2025
- “Online Continual Learning With Maximally Interfered Retrieval”, Aljundi et al 2019
- “Large Language Models Must Be Taught to Know What They Don’t Know”, Kapoor et al 2024
- “Existence of the Core in Approval-Based Committee Elections”, Becker et al 2026
- “Beyond Parameters: Exploring Virtual Logic Depth for Scaling Laws”, Zhu et al 2025
- “Mixture-Of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation”, Bae et al 2025
- “Distributed Attacks in Persistent-State AI Control”, Hills et al 2026
- “Password-Activated Shutdown Protocols for Misaligned Frontier Agents”, Williams et al 2025
- “Incoherent Values? Probing LLM Preferences Through Parametric Variation”, Ajayi et al 2026
- “Instruct Vectors: Base Models Can Be Instruct Models With Activation Vectors”, Eriskii 2026
- “The Emergent Symbolic Structure of Artificial Neural Networks”, McCoy et al 2026
- “Managerial Conservatism and Rational Information Acquisition”, Rasmusen 1992
- “Mathematical Exploration and Discovery at Scale”, Georgiev et al 2025
- “Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment”, Chung et al 2026
- “Estimating Tail Risks in Language Model Output Distributions”, Angell et al 2026
- “Sycophantic AI Makes Human Interaction Feel More Effortful and Less Satisfying over Time”, Ibrahim et al 2026
- “Mold: A Massively Parallel Linker”, Ueyama 2026
- “Towards Scalable and Stable Parallelization of Nonlinear RNNs”, Gonzalez et al 2024
- “Modular Pretraining Enables Access Control”, Roland et al 2026
- “Prompt Baking”, Bhargava et al 2024
- “Happy Guys Finish Last: The Impact of Emotion Expressions on Sexual Attraction”, Tracy & Beall 2011
- Wikipedia (5)
- Miscellaneous
See Also
Gwern
“Tea: Steeped or Shaken?”, Astra et al 2026
“Lighthaven Flood Risk”, Astra et al 2026
“Why Shakespeare Drew Crowds”, Astra et al 2026
“She’s She, and I’m I”, Gwern & Claude-5.1-Fable 2026
“Frutiger Ero”, Gwern & Pro 2026
“LLM Time Travel Visualization”, Gwern 2026
“Sleepcat Purrkit”, Gwern et al 2026
“The Repugnant Conclusion”, Gwern & 2 2026
“Lean Software Scaling Laws”, Gwern 2025
“Face Recognition Training App”, Gwern 2026
“Sand, Rain, Wood”, Gemini-3.1-pro-preview et al 2026
“𝑃𝑒𝑟𝑖𝑠𝘩𝑒𝑑 𝑃𝑎𝑟𝑎𝑑𝑖𝑠𝑒 Graveyard”, Gwern 2023
“Chapter 6, Mime Molting: What to Expect”, Claude-4.8-opus et al 2026
Links
“How Curl Was Accidentally Turing-Complete for 9 Months”
“Tallis, Spem in Alium © (40-Voice Motet)”
“Introducing Gemini 4 Carbon”
“Exposing AdFection: How Discover-Tech Turned Targeted Ads Into a Pipeline for Zero-Click Mercenary Spyware”
“Vowz Bar Recommended Cocktails Menu”, Bar 2026
“Binding Atlas”
“Complete Finite Simple Group Classification Proof in Lean”, Axiom 2026
“Concerning Behavior from a Popular Open-Weight AI Model: Inside a Closed Testing Sandbox Managed by Cohere, One of Alibaba's Newest Qwen3.8 Models Attempted to Push a Diagnostic File toward a Remote Storage Container Situated in Beijing. Just prior to Taking This Action, the Model's Reasoning Stream Had Explicitly Stated That Zero Tools Would Be Triggered”, Cohere 2026
“Interactions Are Generally Not Important in Social Science”, Kirkegaard 2026
“Interactions Are Still Not Important: Not in Medical Data Either”, Kirkegaard 2026
Interactions are still not important: not in medical data either
“Neuron Persona Library”
“Fermi Poker”
View External Link:
https://www.lesswrong.com/posts/JFYvJqMaLw9nhfrur/fermi-poker
“Robustified ANNs Reveal Wormholes Between Human Category Percepts”, Gaziv et al 2023
Robustified ANNs Reveal Wormholes Between Human Category Percepts
“Attention Is Not What You Need”, Chong 2025
“How to Run Turing-Complete Malware in PyTorch’s Backward Pass”
How to Run Turing-Complete Malware in PyTorch’s Backward Pass
“Spending 10 Months Building the Most Human-Like Chess Bot”, mbuffett 2026
“lgit: Source Control for the AI Era”, Brenner 2026
“Make or Buy: The Economics of Decision Models”
“Doing Business In Japan”, McKenzie 2014
“How Does Claude-5.1-Fable Hide Messages in Images?”
“Every AI Model Has the Same ‘Controversial’ Take on Humans”
“How Far Will AI Assistants Go for a Refund They Can’t Get? Spamming the Government, Using a Sick Mother As Leverage and Threatening the Small Claims Court”, Glynn-Henley 2026
“Shichiri Beach in Sagami Province (36 Views of Mount Fuji)”
“Investing in the Public Benefit”, Anthropic 2026
“Aerolamp: Far UV 222nm Lamp—Germicidal Far UVC Light Room Sanitizer”, Aerolamp 2026
Aerolamp: Far UV 222nm Lamp—Germicidal Far UVC Light Room Sanitizer
“Diffusion at Scale: Introducing Mercury 3”
“The Predominance of ‘7’ and the Apparent Spontaneity of Numerical Choices”, Kubovy & Psotka 1976
The predominance of ‘7’ and the apparent spontaneity of numerical choices
“AI Models Can Provably Hide Arbitrary Capabilities”, Draguns et al 2026
“The Role of Personality and Intelligence in Assortative Mating”, Escorial et al 2012
The Role of Personality and Intelligence in Assortative Mating
“Quantum-Computable One-Way Functions without One-Way Functions”, Kretschmer et al 2024
Quantum-Computable One-Way Functions without One-Way Functions
“Training Language Models via Neural Cellular Automata”, Lee et al 2026
“Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors”, Dubiński et al 2026
Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors
“A Founder Population Reveals Genetic Variation With Major Effect on Serious Mental Illness”, Gerdes et al 2026
A founder population reveals genetic variation with major effect on serious mental illness
“Zen Puzzle Garden Is NP-Complete”, Houston et al 2011
“Why Backdooring Neural Networks Is so Easy?”, Seddik & Seddik 2026
“Toward Robust Non-Transferable Learning: A Survey and Benchmark”, Hong et al 2025
Toward Robust Non-Transferable Learning: A Survey and Benchmark
“‘As a Language Model…’: Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It”, Maczan 2026
“Soft Contamination Means Benchmarks Test Shallow Generalization”, Spiesberger et al 2026
Soft Contamination Means Benchmarks Test Shallow Generalization
“Generative AI Floods and Dilutes the Market for Books”, Chakrabarty et al 2026
“DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale”, Huang et al 2026
DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale
“ECO: An LLM-Driven Efficient Code Optimizer for Warehouse Scale Computers”, Lin et al 2025
ECO: An LLM-Driven Efficient Code Optimizer for Warehouse Scale Computers
“Adversarial Poetry As a Universal Single-Turn Jailbreak Mechanism in Large Language Models”, Bisconti et al 2025
Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
“Stealing Reasoning Traces from Proprietary LLM APIs”, Panfilov et al 2026
“Souper-Model: How Simple Arithmetic Unlocks State-Of-The-Art LLM Performance”, Maiti et al 2025
Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
“Benchmarks for Detecting Measurement Tampering”, Roger et al 2023
“Compression Is All You Need: Modeling Mathematics”, Aksenov et al 2026
“Score Centering Stabilizes Off-Policy Reinforcement Learning”, Marek & Ryabinin 2026
Score Centering Stabilizes Off-policy Reinforcement Learning
“Two Parallel Lineage-Committed Progenitors Contribute to the Developing Brain”, Dundes et al 2025
Two parallel lineage-committed progenitors contribute to the developing brain
“Likelihood-Free Hypothesis Testing”, Gerber & Polyanskiy 2022
“Digital Red Queen: Adversarial Program Evolution in Core War With LLMs”, Kumar et al 2026
Digital Red Queen: Adversarial Program Evolution in Core War with LLMs
“FlashAccel: Leveraging High-Bandwidth Flash (HBF) for High-Throughput LLM Inference”, Wang et al 2026
FlashAccel: Leveraging High-Bandwidth Flash (HBF) for High-Throughput LLM Inference
“RoboTTT: Context Scaling for Robot Policies”, Jiang et al 2026
“Crossing the Streams: SSH Plaintext Recovery via a Common Compression Context in Multiplexed Channels”, Bäumer & Brinkmann 2026
“How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks”, Ansari et al 2026
“Brain Drain or Brain Gain? Effects of High-Skilled International Emigration on Origin Countries”, Batista et al 2025
Brain drain or brain gain? Effects of high-skilled international emigration on origin countries
“Online Continual Learning With Maximally Interfered Retrieval”, Aljundi et al 2019
Online Continual Learning with Maximally Interfered Retrieval
“Large Language Models Must Be Taught to Know What They Don’t Know”, Kapoor et al 2024
Large Language Models Must Be Taught to Know What They Don’t Know
“Existence of the Core in Approval-Based Committee Elections”, Becker et al 2026
“Beyond Parameters: Exploring Virtual Logic Depth for Scaling Laws”, Zhu et al 2025
Beyond Parameters: Exploring Virtual Logic Depth for Scaling Laws
“Mixture-Of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation”, Bae et al 2025
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
“Distributed Attacks in Persistent-State AI Control”, Hills et al 2026
“Password-Activated Shutdown Protocols for Misaligned Frontier Agents”, Williams et al 2025
Password-Activated Shutdown Protocols for Misaligned Frontier Agents
“Incoherent Values? Probing LLM Preferences Through Parametric Variation”, Ajayi et al 2026
Incoherent Values? Probing LLM Preferences Through Parametric Variation
“Instruct Vectors: Base Models Can Be Instruct Models With Activation Vectors”, Eriskii 2026
Instruct Vectors: Base models can be instruct models with activation vectors
“The Emergent Symbolic Structure of Artificial Neural Networks”, McCoy et al 2026
The Emergent Symbolic Structure of Artificial Neural Networks
“Managerial Conservatism and Rational Information Acquisition”, Rasmusen 1992
Managerial Conservatism and Rational Information Acquisition
“Mathematical Exploration and Discovery at Scale”, Georgiev et al 2025
“Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment”, Chung et al 2026
Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment
“Estimating Tail Risks in Language Model Output Distributions”, Angell et al 2026
Estimating Tail Risks in Language Model Output Distributions
“Sycophantic AI Makes Human Interaction Feel More Effortful and Less Satisfying over Time”, Ibrahim et al 2026
Sycophantic AI makes human interaction feel more effortful and less satisfying over time
“Mold: A Massively Parallel Linker”, Ueyama 2026
“Towards Scalable and Stable Parallelization of Nonlinear RNNs”, Gonzalez et al 2024
Towards Scalable and Stable Parallelization of Nonlinear RNNs
“Modular Pretraining Enables Access Control”, Roland et al 2026
“Prompt Baking”, Bhargava et al 2024
“Happy Guys Finish Last: The Impact of Emotion Expressions on Sexual Attraction”, Tracy & Beall 2011
Happy Guys Finish Last: The Impact of Emotion Expressions on Sexual Attraction