ddboline's Top FindsLoading...
My Zip Isn't Your Zip: Identifying and Exploiting Semantic Gaps Between Parsers
usenix.org·5h·
Discuss: Hacker News
The Fallacies of Management – The Network Is Reliable
xangelo.medium.com·1d·
Discuss: Hacker News
The Blast Playbook
neelsomaniblog.com·23h·
Discuss: Hacker News
Spiral-Bench: A new benchmark measuring LLM sycophancy and delusion
eqbench.com·3d·
Discuss: Hacker News
🤖reinforcement learning
Cursor: 1.5x Faster Moe Training on Blackwell with MXFP8 Kernels
cursor.com·1d·
Discuss: Hacker News
Getting Customer Calls on a $0 Budget: Lessons From a Tutoring Startup
hackernoon.com·1d
Understanding Lambda Functions in Python: Definition, Usage, and Applications
dev.to·2d·
Discuss: DEV
Sign up or login to customize your feed and get personalized topic recommendations
Sign UpLogin
𝗔𝗜 𝗛𝗮𝗹𝗹𝘂𝗰𝗶𝗻𝗮𝘁𝗶𝗼𝗻𝘀: 𝗟𝗲𝘀𝘀𝗼𝗻𝘀 𝗳𝗿𝗼𝗺 𝗣𝗲𝗿𝘀𝗼𝗻𝗮𝗹 𝗘𝘅𝗽𝗲𝗿𝗶𝗲𝗻𝗰𝗲
dev.to·1d·
Discuss: DEV
Research on Conversational Recommender System Considering Consumer Types
arxiv.org·1d
Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data
arxiv.org·2d
🤖reinforcement learning
UNICON: UNIfied CONtinual Learning for Medical Foundational Models
arxiv.org·1d
Script-Strategy Aligned Generation: Aligning LLMs with Expert-Crafted Dialogue Scripts and Therapeutic Strategies for Psychotherapy
arxiv.org·1d
I Spent $78 Learning Why Bash Still Matters in the AI Age
dev.to·2d·
Discuss: DEV
A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks
arxiv.org·2d
🤖reinforcement learning
The Course Difficulty Analysis Cookbook
arxiv.org·1d
Learning with Confidence
arxiv.org·3d
🤖reinforcement learning
ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions?
arxiv.org·1d
What I Learned From a Week of AI-Assisted Coding: The Good, The Bad, and The Surprisingly Counterintuitive
dev.to·1d·
Discuss: DEV
Bisimilarity and Simulatability of Processes Parameterized by Join Interactions
arxiv.org·1d
Accelerated SQL Query Optimization via Hybrid Evolutionary-Reinforcement Learning
dev.to·5d·
Discuss: DEV
🤖reinforcement learning