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


From GPU Scarcity to AI That Works on Your Data — Part 3 of 3 Part 3 closes the hardware discussion with cloud economics, chip competition and overordering, then follows Milind’s work from video understanding to applied AI at Capital One. Writeup · Date unavailable	Writeup	—	—
From Image Captioning to Editable Worlds Marble turns text and images into editable 3D scenes. Its camera control makes that useful today; learning how worlds behave remains a larger challenge. Writeup · Date unavailable	Writeup	—	—
From impressive outputs to practical AI A July 2023 conversation between Latent Space and Practical AI explores what turns model capabilities into useful systems: operations, evaluation, local data, customization and user experience. Writeup · Date unavailable	Writeup	—	—
From Llama’s training budget to the compute an agent needs How model size, data quality, human preferences, and tool use shaped Llama—and the research still needed to make agents more capable. Writeup · Date unavailable	Writeup	—	—
From Memory-Price Forecasts to the Future of Analyst Software — Part 2 of 3 Agents can assemble financial research faster than an analyst can, but judgment, market regimes, and trusted data still matter. Part 2 of 3 follows a forecasting experiment into the economics of AI infrastructure and Microsoft’s software dilemma. Writeup · Date unavailable	Writeup	—	—
From MLOps to LLMOps: The Data Work Behind the Model Fast experiments, reproducible trials, changing inputs, and production feedback belong in the same engineering workflow. Writeup · Date unavailable	Writeup	—	—
From o1’s Thinking Budget to Working Applications — Part 3 of 3 Part 3 of 3 follows the closing Q&A, research AMA recap, and two demos: reasoning limits, immigration drafting, and a prototype that turns o1’s plans into executable code. Writeup · Date unavailable	Writeup	—	—
From On-Policy Learning to IMO Gold: How Much Can One Model Learn? Learning from rewarded attempts, building a competition checkpoint, and confronting the gaps in planning, data efficiency, and research judgment. Writeup · Date unavailable	Writeup	—	—
From Persistent Pixels to Playable Worlds — ICML 2024, Part 1 of 6 Sora explores what video generation can learn about the world. Genie adds frame-by-frame actions. Part 1 follows their mechanisms, demonstrations, and limits on the path toward agent training. Writeup · Date unavailable	Writeup	—	—
From Probability Flows to Reusable Representations — ICML 2024, Part 4 of 6 Part 4 follows flow matching into crystals and discrete tokens, then examines efficient image synthesis, controllable speech, synthetic pretraining data, and DeCAF’s legacy in computer vision. Writeup · Date unavailable	Writeup	—	—
From reasoning benchmarks to the whole software engineering job Why reinforcement learning’s uneven generalization makes workflow context, product design, and learning from mistakes central to Cursor’s ambitions. Writeup · Date unavailable	Writeup	—	—
From Reusable Vision Features to Actions Learned from Video — Part 5 of 6 Part 5 of 6 follows DeCAF’s transfer-learning legacy, Lucas Beyer’s case for captioning and reward tuning, Ashley Edwards’s path from robot imitation to Genie, and Seung Jae Lee’s introduction to tokenized behavior generation. Writeup · Date unavailable	Writeup	—	—