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


Making Transformers Sing: Suno’s Bet on Audio Tokens and Musical Participation Learning to represent sound lets Suno reuse transformer machinery for music. The harder questions are how to generate fast enough for listening, give people useful control, and judge whether a song moves them. Writeup · Date unavailable	Writeup	—	—
MCP: From Copy-Paste Friction to Composable AI Applications Why Model Context Protocol separates tools, resources, and prompts—and how client support, transport, authorization, and governance shape what developers can build. Writeup · Date unavailable	Writeup	—	—
Mission-Critical Inference: From DeepSeek V3 to Production A large model needs more than a fast inference engine: it needs capacity that scales, predictable latency and workflows that keep the product running. Writeup · Date unavailable	Writeup	—	—
Mistral’s path from streaming speech to verifiable agents Voxtral TTS generates speech one frame at a time. The same conversation connects specialized models, enterprise training, formal proofs, and learning from agents that work for hours. Writeup · Date unavailable	Writeup	—	—
Modal’s Agent Infrastructure: From Bursty Jobs to Programmable Compute How a runtime for changing workloads grew into infrastructure for inference, training and agents—with programmable configuration and observable execution at its center. Writeup · Date unavailable	Writeup	—	—
Moonlake’s bet: build the consequences, then render the world Moonlake combines reasoning models, simulation tools, and learned rendering to create interactive worlds with persistent state—and give agents somewhere to learn from their actions. Writeup · Date unavailable	Writeup	—	—
Moving the AI Frontier: Distillation, Data Movement, and Better Specifications Affordable models depend on frontier research. This conversation with Jeff Dean follows that connection through search, chip design, model specialization, and coding agents. Writeup · Date unavailable	Writeup	—	—
MPT-7B: Long Context and Training Without Babysitting How MosaicML combined attention implementations, data choices, and automated recovery—and why cheaper experiments mattered as much as a finished model. Writeup · Date unavailable	Writeup	—	—
Multi-Turn RL: Rewarding Agents for Useful Work From coding agents that do too much to tools that get called but ignored, the training problem is deciding which actions deserve credit. Writeup · Date unavailable	Writeup	—	—
NeurIPS 2023 Recap, Part 2 of 4: Better Data, Visual Instructions, and Search Part 2 follows QLoRA’s four-bit fine-tuning results, DataComp’s controlled dataset experiments, LLaVA’s visual instruction pipeline, and Tree of Thoughts’ search over alternative reasoning moves. Writeup · Date unavailable	Writeup	—	—
NeurIPS 2023 Recap, Part 3 of 4: Search, Tools, Agent Memory, and Attention Alternatives Part 3 moves from an arithmetic puzzle to Minecraft agents, planning tests, and sequence models—examining how capabilities are built and where apparent success breaks down. Writeup · Date unavailable	Writeup	—	—
NeurIPS 2023 Startups, Part 1 of 4: From Model Building to Useful Products Part 1 follows MosaicML, Fireworks and Cursor through model specialization, production inference, synthetic evaluation data and the value of reusing computation. Writeup · Date unavailable	Writeup	—	—