A Bytecode VM for Arithmetic: The Parser
abhinavsarkar.net·3d·
Discuss: Lobsters, Hacker News
🏗️LLVM
cchistory: Tracking Claude Code System Prompt and Tool Changes
mariozechner.at·2d·
Discuss: Lobsters, Hacker News
🗣️Language Servers
If you can generate obfuscated chain-of-thought, can you monitor it?
lesswrong.com·1d
🔒Hardware Security
Context Guided Transformer Entropy Modeling for Video Compression
arxiv.org·17h
🔢SIMD Programming
LoRA-based methods on Unet for transfer learning in Subarachnoid Hematoma Segmentation
arxiv.org·17h
🔢SIMD Programming
Evading Data Provenance in Deep Neural Networks
arxiv.org·17h
🕯️Candle
PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning
arxiv.org·1d
🤖AI
Agent-Based Feature Generation from Clinical Notes for Outcome Prediction
arxiv.org·17h
🤖AI
CAPO: Towards Enhancing LLM Reasoning through Verifiable Generative Credit Assignment
arxiv.org·17h
🏗️LLVM
Unsupervised Multi-channel Speech Dereverberation via Diffusion
arxiv.org·17h
🎨Computer Graphics
H2C: Hippocampal Circuit-inspired Continual Learning for Lifelong Trajectory Prediction in Autonomous Driving
arxiv.org·17h
🌍Distributed Systems
LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points
arxiv.org·17h
🕯️Candle
Towards Alignment Auditing as a Numbers-Go-Up Science
lesswrong.com·23h
🗄️Database Internals
Steering LLM Agents: Temperaments or Personalities?
lesswrong.com·21h
🤖AI
SAMPO: Visual Preference Optimization for Intent-Aware Segmentation with Vision Foundation Models
arxiv.org·17h
🤖AI
Long-term resilience of online battle over vaccines and beyond
arxiv.org·17h
📈Graph Algorithms
Framework I made for general "productivity"
lesswrong.com·1d
🗄️Database Internals
CAMA: Enhancing Mathematical Reasoning in Large Language Models with Causal Knowledge
arxiv.org·17h
🤖AI
Confidence-Diversity Calibration of AI Judgement Enables Reliable Qualitative Coding
arxiv.org·17h
🏗️LLVM
AI-Educational Development Loop (AI-EDL): A Conceptual Framework to Bridge AI Capabilities with Classical Educational Theories
arxiv.org·17h
🤖AI