Search Latent Space

Find your next rabbit hole.

Articles, conversations, profiles, and grounded writeups.

281 results · Filters applied

Try a search:context engineering agents retrieval augmented generation


Bee: Building an Ambient Agent That Remembers and Acts Wearable audio gives Bee context without constant explanation. Turning that context into useful help requires editable memory, selective attention, and careful choices about power and permission. Writeup · Date unavailable	Writeup	—	—
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	—	—
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	—	—
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	—	—
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	—	—
Beyond AlphaFold: Boltz’s Path from Structure Prediction to Molecular Design How evolutionary clues, generative models and inference-time search support molecular design—and why useful predictions still have to survive experiments. Writeup · Date unavailable	Writeup	—	—
Beyond Attention, Toward Everyday Inference — Part 4 of 4 Part 4 of Latent Space’s NeurIPS 2023 recap closes with the common ingredients of attention-free models, their remaining bottlenecks, and the different demands of interactive responses and bulk processing. Writeup · Date unavailable	Writeup	—	—
Beyond the Model API: Tools, Labor, and Expressive Voice — Part 2 of 3 Part 2 of Latent Space’s Q2 2024 recap examines the infrastructure agents need, the work customers will pay for, and the possibilities and limits of ChatGPT’s early advanced voice mode. Writeup · Date unavailable	Writeup	—	—
Beyond the Prompt Box: Building Notion AI’s Interfaces Brushes, database columns, and inspectable programs show how interface design can turn language-model capabilities into useful, controllable work. Writeup · Date unavailable	Writeup	—	—
Bolt.new: Making the Development Environment Part of the Agent Stronger code generation made Bolt possible. A browser runtime, an observable repair loop, and integrated deployment made it useful. Enterprise agents face the same challenge under very different constraints. Writeup · Date unavailable	Writeup	—	—
Brightwave: financial research built from bounded AI systems Selecting evidence, preserving its meaning, and turning it into investment questions—with expert judgment guiding the system. Writeup · Date unavailable	Writeup	—	—
Building agents that can find, fix, and verify their work Claude’s SWE-bench reference agent shows how much depends on tool design. Computer use and robotics extend the lesson to integration cost, reliability, and trust. Writeup · Date unavailable	Writeup	—	—