Evaluating Long-Context Question & Answer Systems
Evaluation metrics, how to build eval datasets, eval methodology, and a review of several benchmarks.
Eugene Yan26 min read
posts
109 stories
Exceptional Leadership: Some Qualities, Behaviors, and Styles
What makes a good leader? What do good leaders do? And commando, soldier, and police leadership.
Eugene Yan4 min readBuilding News Agents for Daily News Recaps with MCP, Q, and tmux
Learning to automate simple agentic workflows with Amazon Q CLI, Anthropic MCP, and tmux.
Eugene Yan7 min readWhy We Think
Special thanks to John Schulman for a lot of super valuable feedback and direct edits on this post. Test time compute (Graves et al. 2016, Ling, et al. 2017, Cobbe et al. 2021) and Chain-of-thought (CoT) (Wei et al. 2022, Nye et al.
Lil'Log (Lilian Weng)35 min readAn LLM-as-Judge Won't Save The Product—Fixing Your Process Will
Applying the scientific method, building via eval-driven development, and monitoring AI output.
Eugene Yan5 min readFrequently Asked Questions about My Writing Process
How I started, why I write, who I write for, how I write, and more.
Eugene Yan11 min readProduct Updates: March 2025 Release Notes
Discover our latest AI improvements including text-based image editing, AI-driven storytelling agents, personalized text-to-video generation, the powerful Imgen 3 model, toggleable prompt augmentation, and enhanced video colorization.
Neural Love Blog2 min readImproving Recommendation Systems & Search in the Age of LLMs
Model architectures, data generation, training paradigms, and unified frameworks inspired by LLMs.
Eugene Yan39 min readProduct Updates: January 2025 Release Notes
Discover our latest AI improvements including enhanced colorization with prompt support, new art styles, automatic sound generation for videos, and more powerful image processing features.
Neural Love Blog2 min readBuilding AI Reading Club: Features & Behind the Scenes
Exploring how an AI-powered reading experience could look like.
Eugene Yan9 min read2024 Year in Review
2024 was a peaceful year of steady progress. With regard to my craft, the prototypes of 2023 were scaled and put into production, and I rediscovered the joy of building in public.
Eugene Yan6 min readIntroducing WorldModel v1: Revolutionary AI Photo Colorization
Experience the our most advanced AI colorization model, offering unprecedented quality and historical context awareness. Now available for free at neural.love!
Neural Love Blog2 min readSeemingly Paradoxical Rules of Writing
With regard to writing, there are many rules and also no rules at all.
Eugene Yan2 min readReward Hacking in Reinforcement Learning
Reward hacking occurs when a reinforcement learning (RL) agent exploits flaws or ambiguities in the reward function to achieve high rewards, without genuinely learning or completing the intended task.
Lil'Log (Lilian Weng)31 min readHow to Run a Weekly Paper Club (and Build a Learning Community)
Benefits of running a weekly paper club, how to start one, and how to read and facilitate papers.
Eugene Yan6 min readMy Minimal MacBook Pro Setup Guide
I just upgraded my personal laptop from a 2019 Intel MacBook Pro to an M4 MacBook Pro. Like all my new devices, instead of restoring from a backup, I try to Marie Kondo my digital life and start from a clean slate. This also lets me reexamine my existing tools and explore new options.
Eugene Yan5 min readIntroducing Video Generation: Transform Images into Motion with neural.love
Experience state-of-the-art video generation powered by MiniMax Video 01. Convert static images to videos or create videos from scratch with unprecedented ease and quality.
Neural Love Blog2 min read39 Lessons on Building ML Systems, Scaling, Execution, and More
ML systems, production & scaling, execution & collaboration, building for users, conference etiquette.
Eugene Yan9 min read
Showing 54 of 109 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts