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


Retrieval After RAG: Search Built Around Storage, Concurrency, and Cost An unaffordable recommendation feature led to Turbopuffer’s storage architecture. Agents issuing many searches at once are now changing its workload and economics. Writeup · Date unavailable	Writeup	—	—
RLHF 201: From Preference Labels to Model Behavior How instruction tuning, reward models, and DPO turn feedback into model updates—and why the resulting behavior remains difficult to predict. Writeup · Date unavailable	Writeup	—	—
RWKV: Recurrent Language Models Meet a Website-Sized Problem A browser-testing problem leads to cheaper token processing, multilingual models, and a crucial distinction: processing a long input is not the same as remembering it. Writeup · Date unavailable	Writeup	—	—
SAM 2: How an Interactive Demo Shaped Video Segmentation Selecting an object is the beginning. SAM 2 connects tracking, correction and training data through an interface designed alongside the model. Writeup · Date unavailable	Writeup	—	—
SAM 3: Finding Every Instance—and Defining What Counts Concept prompts let users name what they want to see. SAM 3’s architecture, data engine and deployment examples explain how that request becomes masks and tracks—and where human intent still matters. Writeup · Date unavailable	Writeup	—	—
Sam Schillace: Think with the Model, Plan with Code A March 2024 conversation about combining model reasoning with software workflows—from a stubborn output format to a thousand-call textbook generator. Writeup · Date unavailable	Writeup	—	—
Seek.ai: Turning data questions into trustworthy answers Sarah Nagy’s case for natural-language analytics starts with interrupted analysts and waiting colleagues. The challenge is making generated queries dependable enough to guide business decisions. Writeup · Date unavailable	Writeup	—	—
Segment Anything and the Work Between a Vision Model and a Useful App From camera-based board games to interactive segmentation, Roboflow’s story shows how better models change annotation, deployment, and the economics of computer vision. Writeup · Date unavailable	Writeup	—	—
Self Pre-Training and Fair Long-Sequence Benchmarks — Part 4 of 4 Part 4 of 4 of Latent Space’s ICLR 2024 recap examines how pre-training on task data changes the comparison between transformers and recurrent models—and lets simpler architectures close the gap. Writeup · Date unavailable	Writeup	—	—
Serverless AI infrastructure starts below the function decorator Modal connects fast container startup, Python orchestration and GPU utilization to make custom cloud workloads easier to run—and economical to scale. Writeup · Date unavailable	Writeup	—	—
Serverless Browsers and the Infrastructure Behind Computer-Using Agents Browserbase combines hosted browsers, natural-language automation and human takeover to handle the state, access and reliability problems beneath an agent’s clicks. Writeup · Date unavailable	Writeup	—	—
SF Compute: Making GPU Time Tradable Short experiments need flexible compute. Hardware financing needs long commitments. SF Compute connects them through resale, short reservations, and standardized delivery. Writeup · Date unavailable	Writeup	—	—