Archive
Everything we've scored that's past the 48-hour window — open to everyone, no account needed. The live feed only shows what's moving right now; this is the record behind it.
- 19Concept Drift Detection and Adaptive Retraining of Malware Classification Models
- 19An Exploratory Evaluation of LLM-Assisted Rewriting of Moderate-Complexity Financial Sentences for DisCoCat-Based Sentiment Analysis
- 19Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data
- 19PsychoAgent: An Affect-Sensitive Cognitive Architecture for Conflict-Aware Memory in LLM Agents
- 19Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
- 19DynaCrys: Crystal Generation with Dynamic Space-Group Diffusion
- 19Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers
- 19Benchmarking the Benchmarks: Evaluating Benchmarks for Conversational Agents
- 19MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification
- 19FinRank: An Evidence-Grounded Benchmark for Financial Question Answering and Retrieval over SEC Filings
- 19SABRE: Scalable and Automated Benchmarking of VLMs under Stress
- 19Recommender regret for improving regularised RL estimation with bandits and MCTS
- 19Mesoscopic learning dynamics of extensive-width neural networks
- 19Knight Capital: how a reused feature flag lost $460 million
- 19Rethinking Expressivity and Efficiency in Test-Time Training
- 19Multiplicative Optimism for Constant Regret in Games
- 19Expected Free Energy-based Informative Path Planning for Robotic Mars Exploration
- 19Wasserstein Policy Gradient for Entropy-Regularized Linear-Quadratic Control
- 19Uncovering expert objectives in production planning via inverse optimization: An industrial case study
- 19Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits
- 19You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model
- 19SPARCL: Spectral Partitioned Analytic Continual Learning
- 19TEPA: Revoking Stale Memories for Conflict-Robust Language Agents
- 19Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning
- 19How Proper Scoring Rules Shape LLM Forecasting
- 19A Picture is Worth a Thousand Tokens: How Vision Language Models Cut AI Energy Costs While Improving Accuracy
- 19Information Satisfaction: A Reader-Centered Axis for Summarization Evaluation
- 19Shift Aware Transfer Learning with Adaptive Dual-Encoder Fusion for PM Forecasting in Data-Limited Environments
- 19I built a complete DJ console in a single HTML file using Web Audio API
- 19Logic-Guided Graph Denoising Diffusion Models
- 19NL2AGBench: Benchmarking LLM Auto-Formalization for AlphaGeometry
- 19Universal Semantic Enhancement for Weakly Supervised Anomaly Detection
- 19CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing
- 19Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge
- 19SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning
- 19Cloud-Boosted Low-Compute Multi-Channel Speech Enhancement
- 19Write prompts for the cache, not the reader
- 19Building a smart greenhouse in the woods: the architectural experiment of DevFest Basilicata - DevF{or}est
- 19DevRelCon, Adult Summer Camp, and My First Time Speaking
- 19From Flow-Box Invariants to Global Conservation Laws: Machine Learning-Assisted Detection of Singularities and Near-Integrability
- 19Benchmarking and Enhancing LLMs for Rule-Intensive Review of National Standard Documents
- 19Does FLAIR super-resolution erase or hallucinate small white-matter lesions?
- 19NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities
- 19QUASAR: A Quantum-Classical Neural Network for SAR Satellite Physical-Layer Authentication
- 19Odin 1.0 Announcement
- 19LoCA: Enabling Multi-Modality in Geospatial Location Encoders
- 19ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL
- 19COVER: Identifiable Evaluation of Coalition Routing
- 19RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction
- 19Structural Chain-of-Thought: Reasoning with Executable Computational Graphs
- 19RELAGRAM: Recursive Latent Graph Model for the Capacitated Vehicle Routing Problem
- 19Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
- 19Rule-Compliant Visual Spatial Planning for Multimodal Large Language Models
- 19Green Code or Costly Code? Evaluating the Energy Costs of Iterative LLM-Based Code Optimizations
- 19Closing the Modality Gap via Simplex-Constrained Representations
- 19Learning Cardiac Features: ECG Biometrics Across Time and~Exercise
- 19Growth Without Us: Machine Consumers, Corporate Circularity, and the Decoupling of GDP from Humanity after AGI
- 19HarnessOpt-Bench: Evaluating LLMs at Harness Optimization
- 19Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors
- 19RegExtract: A Benchmark for PFAS Regulatory Information Extraction with LLMs
- 19When Human Corrections Travel: Safety in Federated VLA Adaptation
- 19Reinforcement Learning with Multi-Step Transition Predictions: A Bellman Theory
- 19VocalGrad: Evaluating Acoustic Perception in Audio Language Models
- 19Real-time virtual circuits for plasma shape control via neural network emulators: experimental demonstration on MAST Upgrade
- 19Prompt-Conditioned Channel Attention for Hierarchical Feature Modulation toward Anatomy-Agnostic Segmentation
- 19On-Policy Self-Distillation without Any Supervision
- 19AUSO: Action-Level Unified Skill Optimization from Internalization to Utilization
- 19QuanTiMedAI: Quantum-Enhanced Time-Series Model guided by Agentic AI for Cardiac Arrest Mortality Prediction
- 19Schedule optimization for tau-leaping in masked discrete diffusion
- 19The Italian lawmaking process: a unified and structured dataset
- 19I Built Nabsun: An Open-Source AI Browser That Works in Your Real Tabs
- 19Stranger, Fan, or Peer? A Systematic Study on the Role of Interlocutor in Persona-Based Dialogue Generation
- 19NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering
- 19Random Feature Pruning for Multi-Class Classification
- 19Gravitational-wave parameter estimation with machine-learning generated surrogate waveforms
- 19BaKron: Efficient Quantization with Kronecker-Factored Hessians
- 19Surv-IPTB: An Attention-Based Model for Estimating Individual Probability of Treatment Benefit with Survival Data
- 19Memory Augmentation Unlocks Efficient Chain-of-Thought Reasoning
- 19NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding
- 19Advancing SVD-based LLM Compression via Layer-Wise Error Model Search
- 19The Tamed Subgradient Unadjusted Langevin Algorithm beyond Convexity
- 19LagNet: Lag-Structured Operators for Long-Term Time Series Forecasting
- 19RACER: Role-Aligned Competence Estimation for Human-AI Routing
- 19InsufficiencyBench: Evaluating LLM legal advice on underspecified user queries
- 19Trusting the Tool: Asymmetric Deference of LLM Vulnerability Auditors to Static-Analysis Evidence
- 19The Exceedance Design Effect: Effective Sample Size for Thresholds under Clustering
- 19Anchors Enhance Controllability and Reasoning of Diffusion Language Models
- 19Electronic Navigational Chart Change Classification
- 19Do "True" and "False" Add Up to One? Complement Consistency in LLM-Agent Opinion Simulations
- 19J-Comm: Jacobian-Guided Latent Communication between LLM Agents
- 19From Deliberately Constructed Systemic Representations of the World of Activity to Dialogue: A Five-Level Communication Architecture for Strong Language-Based ASI
- 19Stochastic Dynamics on Persistence Diagram Space via Reinforcement Learning
- 19Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference
- 19Swarm Telepathy: Prefill-Free KV-Cache Transfer Across Families
- 19Learning to Move Cities: Deep Meta-Models and Reinforcement Policies for Calibration and Control in Urban Networks
- 19Interpretable sparse fine-tuning with TopKLoRA enables faithful circuit discovery
- 19The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images
- 19CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment
- 19ConceptTS: LLM-Guided Concept Bottlenecks for Interpretable Multivariate Time-Series Forecasting
- 19unsloth/embeddinggemma-2-GGUF (feature-extraction)
- 19Guiding Agents of Quantum Games to Equilibrium using Matrix Exponential Fixed-Point Iteration
- 19TurnCost: Turns, Not Observations: Cache-Aware Loop Engineering for Coding Agents
- 19VLCQ: Post-training quantization for deep neural networks using variable length coding
- 19ContractScrub: A benchmark for final review of legal contracts
- 19All Core Devs - Consensus (ACDC) #190, October 29, 2026
- 19When Should a Failing Robot Ask? Initiating Corrective Human-Robot Dialogue from Audited Sensor Evidence
- 19On the Transferability of Agricultural Weed Detection Under Cross-Field Distribution Shift
- 19EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering
- 19Have You Been Convinced? A Neuro-symbolic Argumentation Reasoning Approach to Detecting Persuasiveness in ChangeMyView Discussions
- 19TRACE-C: Rank-Calibrated Relational Anomaly Detection for Multi-Stream Operational Telemetry
- 19We don't need Chromium. We can just generate Native PDFs from the Browser’s Resolved Layout
- 19Benchmarking Patent Drafting from Inventor-Style Disclosures
- 19It Passed Because It Never Looked
- 19Adapting Knowledge Graphs for Behavior Denoising in Sequential Recommendation
- 19A charity does not close because its overhead was too high. I checked 328,186 tax returns.
- 19Affective Context Amplifies Sycophancy in LLM Responses
- 19AI Coding Tip 031 - Stop Over-Prompting Reasoning Models
- 19RARE: Decoupling Representation Steering from Expert Routing in Mixture-of-Experts Language Models
- 19Advanced Linear Algebra with Applications - Part I (Numerical linear algebra for PDEs, machine learning, and data assimilation)
- 19How parallel AI agents should talk to each other (and the bug that proved it)
- 19A 32-year-old bug walks into a Telnet server
- 19The Bounded Context Is the Scope the Agent Actually Needs
- 19Self-Evolving Visual Agent via Margin Reward
- 19Porting a 20-Year-Old Game to Mobile: Lessons from RuneScape
- 19NixOS for government: why the Netherlands is leaving Microsoft
- 19GAMW: Generation-Aware Mel-Domain Watermarking for TTS Traceability
- 19Automating CI/CD Pipelines for Cypress Testing with GitHub Actions
- 19Knowledge transfer between simple discrete worlds
- 19Rescue Me: ember-website
- 19On the Theoretical Limits of Learning Unconstrained Interatomic Potentials
- 19Manusagents/GPT-5.5-Gemini-3.1-Pro-Grok-4-Claude-Fable-5-Mythos-5-Qwen-3.7-Max-and-more-Distillation-Dataset (dataset)
- 19EIPIP Meeting #130, Sep 16, 2026
- 19Toward a Multimodal Foundation Model for Plasma State Reconstruction
- 19COSMIC DE’s First Seven Months
- 19Claude is stuck on a question. Answer it from Discord.
- 19When Data Centres Move In
- 19Technically Right, Organisationally Impossible
- 19Pour one out for Infrastructure Composer
- 19Update a Git branch without checking it out
- 19I built pseudonymous Discord chat — and the hard part was not hiding usernames
- 19STAY - Keep the Days You Got
- 19Ignition: Flashing 2,300 conference badges with Temporal
- 19What does your CDK app cost when nobody is using it?
- 19Danfoss cyberattack: French fridge controls and the reset warning
- 19I Added llms.txt to Four of My Websites - Here’s What I Learned
- 19The Key's Owner Wasn't the Spender
- 19HypeBESTIE: My Free Sincere Compliment Engine
- 19DogeVault Stylist — AI Dog Fashion Stylist
- 19The Boundary Independence Principle (BIP)
- 19Stop Leaking API Keys: The Backend for Frontend (BFF) Pattern Explained
- 19Every DIY Project Starts as Automation and Ends as Art
- 19Your eval suite passes. I built the tool that checks whether it checks anything.
- 19Claude Code Subagent Error Recovery in 2026: Retry Logic, Fallback Strategies, and Detecting Stuck Loops
- 19Atom is better than RSS, in ways that matter
- 19The future, after AI
- 19A fake alert can copy your bank's words. It can't know your balance.
- 19The move the agent is not allowed to make
- 19Your README Is a Lie Until Someone Else Runs It
- 19When a Safety Reviewer Rejected Everything and Still Passed Its Test
- 195 attempts, 2 SIGKILLs, 1 non-existent flag: how I got a 4-second avatar to speak Spanish
- 19Learning neural networks through mental models
- 19The sparring partner was reading my config file
- 19Build semantic search inside video: shot embeddings + transcript chunks, fused on the timeline
- 19THE SERVER HAD THE DATA. BUT NOT THE KEY.
- 19AI Won't Kill Your AI Won't Kill Your Motivation. But Mediocrity Might.
- 19I spent 11 days optimizing a search ranking that only I could see
- 19How passkeys work: WebAuthn, phishing and why you can't move them
- 19Tickmark: bank statements to spreadsheets, checked to the cent, without uploading them
- 19AI Content Pipeline Safety: The Claims Gate That Stops Fabricated Customer Results
- 19The Vacuum Approaches — you are the dog
- 19Adaptive RAG: Designing Retrieval Pipelines That Choose the Right Strategy at Runtime
- 19Your canvas "A4 export" is not A4: DPI, print size, and the number nobody checks
- 19useFieldArray is not updating across steps — and why it can't
- 19Renting Out One T4 to Three Customers: Gemma 4, vLLM Multi-LoRA and a Rust Gateway
- 19Static Analysis Told Me My React App Had a Problem. Runtime Profiling Told Me Which One
- 19Stochastic Parrot or Alien Mind? What Really Is An LLM?
- 19Open Call: an agent that says where every hackathon fact came from
- 19We found a bug that let our test suite write to production. Here's what we did about it.
- 19Three small design decisions in a "toggle effects via CSS class" library, and the tradeoffs behind them
- 19How I Planned an Italy Trip with an Agentic Workflow
- 19Warp's Ben Holmes on Building the Software Factory
- 19A thoughtful JSON editor with line flags — the tool I always wished existed for handling JSON payloads.
- 19I couldn't find a good Google Trends MCP. So I just built one
- 19I have a picture with a mapped area that by clicking on it opens a mp4 video in a highslide frame
- 19Your Python code is already assembly. I made it runnable.
- 19CrowdStrike outage explained: 21 fields, 20 slots, 8.5M blue screens
- 19Preventing Duplicate Side Effects in Event-Driven Systems
- 19Stealing Reasoning Traces from LLM APIs: How It Works and What to Audit
- 19Gemma 4 in Pure JAX: What Changes Between Turing and Ada, and What Doesn't
- 19Tales of a Dev - An Alternative Reality
- 19Sharing Pieces of My AI Agent Workflow
- 19No Results Found (Until You Look)
- 19I Read 25 Release Pipelines Looking for One Bug. Four Had It.
- 19Exposing AI Inference as a Telco Network API over the 5G User Plane
- 19I got tired of SSHing into 10 VMs a day, so I built a live map of my whole infrastructure
- 19include-tidy: A Tool to Enforce Include-What-You-Use, Part 2
- 19Multirun: A Multi-Agent Run Framework
- 19I Built a Personal AI That Actually Knows My Projects (RAG + Ollama, Zero Cloud)
- 19Designing a User Management system with JWTs, Ktor, and Exposed
- 19Sphinx — your neighbourhood, turned into riddles