27 posts with this tag.
OpenAI's first domain-specific frontier model for life sciences, gated behind a trusted-access program rather than released to the public
If AI agents are going to do real work, the prompt is only one part of the setup. The interface around the AI matters more.
ICLR 2026 paper introducing ACE, a framework that treats LLM contexts as self-evolving playbooks instead of static prompts
The discipline of designing everything around an AI model that makes it reliable in production
The discipline of filling an LLM's context window with the right information for each step, replacing prompt engineering as the core AI skill
Multi-session orchestration where independent Claude instances coordinate through shared tasks and direct messaging
Original source for the Ralph Wiggum autonomous AI coding technique and context engineering philosophy
Modular knowledge packages Claude loads on-demand when your task matches their description
Shell commands that run at specific points in Claude Code's lifecycle for automation and validation
Complete reference for built-in and custom slash commands in Claude Code
Autonomous AI coding technique using persistent iteration loops until task completion
GitHub's Spec Kit gives AI agents structure. The Ralph Wiggum loop gives them persistence. Together, with the right prompt, they solve the two biggest problems in agentic coding.
Isolated AI workers in Claude Code with their own context windows, tools, and permissions
Official European Commission tool for assessing AI system compliance with EU AI Act requirements and risk classification
Open-source toolkit for spec-driven development with AI coding agents
Development methodology where specifications become the primary artifact and code is generated from them
A webcam-controlled air hockey game where two players use their index fingers as paddles, built to stress-test Gemini Pro 3 in Google AI Studio
Research framework for crafting and evaluating constitutional principles that actually work in AI alignment
Anthropic's training methodology that uses AI feedback instead of human feedback to align models
Extracting implicit principles from preference data by inverting the Constitutional AI process
Open standard for connecting AI models to external tools, data, and systems via a unified interface
Anthropic's terminal-first coding agent that reads your codebase, runs commands, and ships code autonomously
LLMs can write code, but they're terrible at design. Here's why they default to purple gradients and three-box layouts, and what you can actually do about it.
Democratic approach to AI alignment where populations source principles through deliberation
A web app that turns vague task descriptions into production-ready AI prompts using proven prompt engineering patterns
LLMs can write code, but they're terrible at design. Here's why they default to purple gradients and three-box layouts, and what you can actually do about it.
Model Context Protocol servers promise to solve LLM limitations, but they introduce security vulnerabilities and architectural complexity that most people aren't discussing.