Search Latent Space

Find your next rabbit hole.

Articles, conversations, profiles, and grounded writeups.

2093 results

Try a search:context engineering agents retrieval augmented generation


Lilian Weng summarizes 35 papers on Harness Engineering for RSIAI News · 2026-07-08	AI News	—	2026-07-08
Ben Holmes Software developer and educator building AI-assisted tools for development, conversation, and personal knowledge. Person · 2026-09-17	Person	—	2026-09-17
The Field Guide to FableAI News · 2026-07-07	AI News	—	2026-07-07
Ben Poole Machine-learning researcher whose collaborative work spans diffusion models, text-to-3D generation, dynamic scene reconstruction and neural-network learning. Person · 2026-09-20	Person	—	2026-09-20
AIEWF Daily Dispatch: The great loops debate and the state of AI engineeringArticle · Richard MacManus · 2026-07-03	Article	Richard MacManus	2026-07-03
Benchmarks 101: What a Model’s Score Actually Tells You A benchmark tests particular capabilities under particular conditions. Understanding those choices helps explain both model progress and the gap between a leaderboard score and a useful product. Writeup · Date unavailable	Writeup	—	—
Vercel's Andrew Qu on why agents are a new kind of softwareArticle · Richard MacManus · 2026-07-03	Article	Richard MacManus	2026-07-03
Benchmarks 201: What a Leaderboard Score Actually Measures Clémentine Fourrier on reproducible comparisons, the limits of preference rankings, and the engineering choices behind model scores, from the July 2024 conversation. Writeup · Date unavailable	Writeup	—	—
The website of the future may assemble itself for every visitorArticle · Richard MacManus · 2026-07-02	Article	Richard MacManus	2026-07-02
Benchmarks, Self-RAG, and Step-by-Step Verification — Part 3 of 5 Part 3 follows an agent’s failed travel plan into the science of benchmarks, then examines how Self-RAG and process supervision use intermediate judgments to select better outputs. Writeup · Date unavailable	Writeup	—	—
Skill engineering and the case against one-shot AI designArticle · Richard MacManus · 2026-07-02	Article	Richard MacManus	2026-07-02
Better training data starts with what the model still needs to learn Datology’s case for optimizing filtering, rewriting and training order together—and measuring their value in learning efficiency, model capability and inference cost. Writeup · Date unavailable	Writeup	—	—