Videos

Personal AI assistants can now negotiate bills, cancel subscriptions, and even control a Tesla when given API access...

Generic AI output is almost always a clarity and destination problem, not a model problem: the presenter's five-move...

Matt Pocock's Claude skill process comes down to five steps: notice what you keep sending back, lean on leading...

GEPA is a reflective optimization technique that achieves large performance gains from very few samples by using...

Splitting a voice agent's prompt into per-step contexts cuts token usage by more than half in production, according...

Replicating the IFScale benchmark shows the old 200-instruction ceiling is obsolete: today's frontier models hold...

Deleting most of your Claude skills and system prompts can make the model smarter, not dumber. The creator of Claude...

Generic responses from AI can be eliminated by providing five layers of context: voice, knowledge, collaborative,...

Building reliable agents requires a systematic evaluation approach that starts with intuitive checks and scales to...

Fable 5 is an expensive reasoning model intended for strategic, multi-step tasks, not quick chatbot usage. By...

Loop engineering is the latest evolution in agent scaffolding, stacking another autonomous loop outside of harness...

The prompt interface for large language models is structurally identical to the batch-processing punch card: the...

Claude Fable 5 is a powerful but expensive model that benefits from short, clear prompts with context, negative...

The talk presents a checklist for writing great agent skills, covering trigger (user vs model invoked), structure...

Rachel Lee Neighbors argues that developers can drastically cut costs, improve latency, and enhance security by...

A single system prompt fails to handle brand identity, situational context, voice nuance, and output verification...

Claude Code can be upgraded with four specific strategies to transform it from a productivity tool that agrees too...

Claude can be used far beyond simple Q&A by leveraging its seven levels: choosing the right mode (chat, co-work,...

Agent loops replace the human in the feedback/iteration cycle by having the AI reason, act, and observe until a...

Six power phrases unlock 10x productivity with Claude Code by changing how AI projects start, scale, and run. The...

Most people building Claude skills waste time perfecting the instructions (the brain) while ignoring the face—the...

Fable 5 is the biggest model improvement since GPT-4, but using it effectively requires the right harness (Cursor or...