I taught Claude to talk like a caveman to save my AI tokens. It became unusable — and I learned a lesson about virality.

Alexander Huso taught Claude to talk like a caveman to save tokens from his Pro plan. The resulting quality was poor, and he ...

My aging family kept falling for scams. For $20, I built a no-code app to protect them.

Matter Sanner, 54, vibe coded an app using Cursor called ScamSkeptic for his aging family, who had fallen victim to scams.
Journal of Medical Internet Research

Passive Sensing for Mental Health Monitoring Using Machine Learning With Wearables and Smartphones: Scoping Review

Passive sensing via wearable devices and smartphones, combined with machine learning (ML), enables objective, continuous, and noninvasive mental health monitoring. Objective: This study aimed to ...
GitHub

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

Developing autonomous LLM agents capable of making a series of intelligent decisioiins to solve complex, real-world tasks is a fast-evolving frontier. Merely relying on human demonstration for ...
IEEE

Human-in-the-loop Learning for Adaptive Robot Manipulation using Large Language Models and Behavior Trees

Abstract: Large Language Models (LLMs) are now transforming the way robots learn to work in unpredictable environments, such as homes or small enterprises. A growing number of approaches are combining ...
IEEE

Detecting Code Vulnerabilities using LLMs

Abstract: Large language models (LLMs) have emerged as a promising tool for detecting code vulnerabilities, potentially offering advantages over traditional rule-based methods. This paper proposes an ...