
Diffusion Language Models: How Mercury Changed the LLM Speed Game
Diffusion language models like Inception Labs' Mercury draft a whole response and refine it instead of going token by token. See why that makes them so fast.
Page 100 of 101
Deep dives into AI agents, coding tools, and building with LLMs.
1202 articles844 topics

Diffusion language models like Inception Labs' Mercury draft a whole response and refine it instead of going token by token. See why that makes them so fast.

xAI's Grok 3 launch explained: the 200,000-GPU cluster, benchmarks against GPT-4o and Sonnet 3.5, the reasoning modes, and what it all means for developers.

Unstract is an open-source, no-code platform that uses LLMs to extract structured JSON from PDFs, invoices and scans. How Prompt Studio and self-hosting work.

OpenAI Deep Research is a ChatGPT agent that turns a research question into a cited report in minutes. How it works, the model behind it, and its limits.

ChatGPT Tasks lets you schedule reminders and recurring jobs in plain language. See how it works, practical use cases, current limits and where it is heading.

Gemini Deep Research plans a multi-step research strategy, verifies sources and writes cited reports. See how it works, Docs and Sheets export, and its limits.

Microsoft PHI-4 is an MIT-licensed 14B model that matches Llama 3.3 70B on key benchmarks. See its specs, how to run it locally with Ollama, and when to use it.

Build an AI agent web app by wiring a Python LangGraph agent into Next.js with CopilotKit - covering the graph, search nodes, streaming state and React UI.

Llama 3.3 70B delivers 405B-class performance at a fraction of the cost. See the benchmarks, pricing versus GPT-4o, where to run it, and when to pick it.

Lovable builds full-stack web apps from prompts with native Supabase auth, database and migrations. See a course platform build, its error handling and limits.

ChatGPT desktop on macOS can now read VS Code, Xcode, Terminal and iTerm2. How to set it up, what the read-only beta does today and where it falls short.

The Realtime API uses WebSockets for two-way voice interaction with function calling and stateful conversations. Here is how to set it up and build on it.
Showing 1189-1200 of 1202 articles
Deep dives on AI agents, coding tools, and building with LLMs - delivered weekly. No spam.
Free forever. Unsubscribe anytime.

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.