Tag
Analysis of 246 open-source repositories and 57 papers on agent harnesses highlights best practices like human-written context, limiting tools, and incremental testing to improve AI agent performance.
The study examines the semantic consistency of LLM-generated replies across different models and conversational contexts, highlighting the need for infrastructure and design strategies to maintain stable responses for conversation-based assessments.
The article analyzes the language distribution in AI agent skills, finding that non-English skills are growing rapidly with Chinese leading, indicating a global shift in AI development beyond English-speaking regions.
This article discusses findings from the AI Observatory project on how people use AI models like ChatGPT and Gemini for different purposes, and critiques Flock Safety's police tech for its design choices affecting civil liberties.
This article offers an in-depth analysis of the Causal World Model (CWM) proposed by Aether AI (原识之智), arguing that the next AI paradigm will shift from correlation to causation. It discusses the theoretical foundations, technical architecture, and potential impact on video generation and embodied intelligence.
This analysis updates the study of DeepSeek's research team, revealing that their talent pool has grown to 356 researchers with increasing citation impact and that over half have only Chinese affiliations, highlighting challenges for U.S. talent retention and independence.
A paper analyzing Claude Code reveals that its effectiveness comes from a simple AI loop surrounded by a robust infrastructure for tools, safety, memory, and recovery, rather than a complex AI brain. The study emphasizes that autonomy increases the burden on infrastructure.
OpenAI releases an analysis demonstrating that compute used in largest AI training runs has grown exponentially at a 3.4-month doubling time since 2012, representing a 300,000x increase and vastly outpacing Moore's Law. The analysis suggests this trend will likely continue and calls for increased academic AI research funding to address rising computational costs.