recommendation

Recommend a high-quality AI tech blog ruxu.dev, authored by Spanish software architect Roger Oriol, focusing on practical content like building AI Agent from scratch, Advanced RAG, Reasoner Models, etc.

ChatGPT has been caught recommending fake scam websites and cloned stores of defunct brands, raising concerns about its training data being poisoned and the safety of AI-powered shopping assistants.

A list of 10 recommended books for becoming a 10x AI engineer, covering LLMs, machine learning, deep learning, and data-intensive systems.

Recommend an excellent article about AI agent infrastructure.

The author built a free quiz-based tool to help developers find suitable, well-maintained AI agent repositories among 50+ options, avoiding broken or outdated repos, and is seeking community feedback.

FindMyAI is a free AI search engine that recommends the best AI tool for any task without requiring signup. It supports 18 languages and aims to help users quickly find suitable AI tools.

Recommends an AI short drama with only 4 episodes released, calling it the highest quality AI short drama to date.

Teknium recommends NetworkChuck's video overview of Hermes Agent, praising its unique features and encouraging others to try it.

A tweet recommending a paper that is described as the bible of distributed inference.

This article discusses whether AI agents should base recommendations on workflow analysis rather than product category, emphasizing that users' true needs are workflow outcomes.

Recommends 8 Chinese tech/AI podcasts covering AI, entrepreneurship, business interviews, etc., including Silicon Valley 101, Zhang Xiaojun's Business Interview Series, Crossing, etc., suitable for listeners interested in AI and tech business.

User seeks an open-source proxy to intercept and debug API calls from AI agents to understand their internal workings, after finding LiteLLM too enterprise-focused.

Recommending a popular academic open-source project recently.

A developer recommends browser-harness for making OpenClaw significantly more useful.

This paper proposes a paradigm shift in context engineering, formulating it as a recommendation problem. The authors introduce Neural Collaborative Context Engineering (NCCE), which uses collaborative filtering to dynamically assign instance-specific contexts, improving LLM task accuracy.

Recommend following Lex Fridman's podcast, which features in-depth interviews with many top figures in AI, covering major AI companies such as OpenAI, Anthropic, Google DeepMind, and is considered the most cutting-edge podcast platform for AI thought.

GBrain now recommends ZeroEntropy as the default embedding and re-ranking option, replacing OpenAI and Voyage AI.

Promotes a one-hour Cambridge lecture by Demis Hassabis that provides deep insights into the future of AI, claiming it will teach more than most learn in five years.

slock has recently updated many practical features and fixed several bugs. The author recommends users update to the latest version to experience it.

The article argues that AI agents need structured, accurate product descriptions beyond marketing slogans to make reliable recommendations, and questions who should provide and verify such data.