Anthropic’s latest Economic Index does not show how many jobs AI has replaced. It shows how work is first changing from chat and assistance into deliverables and deeper task delegation.
-
AI Application Startups: From Selling Tools to Selling Outcomes
A reading note on AI application startups: begin with outsourced, rule-bound work and sell the outcome, not merely a smarter tool.
-
What We Talk About When We Talk About AI-Native Games
From conversational characters and world-aware NPCs to worlds that continue evolving after the player leaves, AI is becoming part of gameplay itself. This essay explores what AI-native games can offer players, and how memory, emergence, and generative freedom must remain grounded in game design.
-
When Code Becomes Cheap
Coding agents make code and prototypes cheap, shifting the scarce resources of software development toward judgment, verification, coordination, learning, and responsibility.
-
Demystifying evals for AI agents (Anthropic)
The capabilities that make agents useful also make them difficult to evaluate. The strategies that work across deployments combine techniques to match the complexity of the systems they measure.
-
Synthetic Data as Engineering: Starting from Terminal-Corpus
Notes on SFT synthetic data engineering, starting from NVIDIA’s Terminal-Corpus and connecting it to classic and recent work on instruction synthesis, taxonomy-driven generation, executable tasks, and curation pipelines.
-
JoyAI-VL-Interaction: From Chat Back to Continuous Interaction
Chat is one way we package generative models, not the natural shape of the model itself. Interaction models return models to continuous tokens, perception, and action, with JoyAI-VL-Interaction as a concrete vision-language example.
-
How Game NPCs Became Agents Before Generative AI
Before LLM agents became popular, game NPCs had already formed a practical agent architecture around perception, state, decision making, and action.
-
Context Is All You Need: Context Engineering for Agents
Treating context as a finite resource: from context rot and attention budgets to storage structures, retrieval pipelines, time-aligned writes, version governance, and runtime techniques such as compaction, reset, subagents, and checkpointing.
-
The Fact Layer and the Interface Layer: Markdown and HTML Aren't Rivals
HTML is tempting. It can turn long AI-generated documents into something readable, clickable, and shareable. But I do not want HTML to quietly become the source of truth. Markdown should keep the diffable, searchable, auditable record; HTML should make complex systems easier to read.