Tag
The author critiques the reliance on papers and conferences as productivity measures in AI research and presents guidelines for making research impact via open-source artifacts.
OpenAI has released the Australian Youth Safety Blueprint, a roadmap outlining six pillars to safeguard young users in AI interactions, focusing on literacy, privacy, and company accountability.
This article addresses the consistency problem in AI agents, where tasks may fail on repeated attempts, and introduces ALTK-Evolve's Consistency Analyzer to diagnose and improve reliability, reducing the consistency gap from 24.4pp to 12.0pp without losing average accuracy.
The paper develops a framework for prompt design in LLM-based robots to prevent hallucinated capabilities and misleading personas, introducing a structured template with eight functional components based on expert surveys and literature review.
A developer shares a comprehensive Agents.md template with core principles for building and maintaining trading systems using AI agents, covering strategy development, engineering standards, and scope discipline.
Hugging Face is collaborating with the Open Secure AI Alliance to develop guidelines for learning from security incidents, with contributions from over 120 members including NVIDIA.
The Open Secure AI Alliance, including NVIDIA, Cisco, CrowdStrike, Hugging Face, and Red Hat, proposes SAFE guidelines to share AI incident findings and strengthen agentic AI cybersecurity, alongside contributions of open-source security tools and models.
Introduces GuideSkill, an external reasoning layer that compiles clinical practice guidelines into executable diagnostic skills, improving LLM accuracy on clinical reasoning benchmarks without backbone updates.
An open-source guide to help write better command-line programs, updating traditional UNIX principles for the modern day.
Introduces the agents-best-practices repository, a production-grade AI agent runtime framework design guide covering tool permission tiers, context compression, etc., supporting Codex and Claude Code installation.
Sharing Andrej Karpathy's 65-line minimal Agents.md configuration that can be directly copied into Codex App's global custom instructions as a starting point to improve AI coding agent behavior.
This paper proposes an iterative moderation framework that refines and reuses annotation guidelines to improve LLM-based annotation performance, validated on biomedical NER tasks with GPT, Gemini, and DeepSeek models.
OpenAI publishes a guide on responsible and safe use of AI, offering best practices for ChatGPT users including keeping humans in the loop, verifying information, watching for bias, and maintaining transparency in AI usage.
A single CLAUDE.md file that implements four principles to improve Claude Code's coding behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.