Daniel Miessler's PAI includes an 'upgrade skill' that allows the system to improve itself. It can ingest new information from engineering blogs or platform changelogs, then recommend and implement upgrades to its own skills and hooks to incorporate new features and knowledge.
Related Insights
Unlike simple chatbots, AI agents tackle complex requests by first creating a detailed, transparent plan. The agent can even adapt this plan mid-process based on initial findings, demonstrating a more autonomous approach to problem-solving.
The next major evolution in AI will be models that are personalized for specific users or companies and update their knowledge daily from interactions. This contrasts with current monolithic models like ChatGPT, which are static and must store irrelevant information for every user.
The popular conception of AGI as a pre-trained system that knows everything is flawed. A more realistic and powerful goal is an AI with a human-like ability for continual learning. This system wouldn't be deployed as a finished product, but as a 'super-intelligent 15-year-old' that learns and adapts to specific roles.
The current limitation of LLMs is their stateless nature; they reset with each new chat. The next major advancement will be models that can learn from interactions and accumulate skills over time, evolving from a static tool into a continuously improving digital colleague.
Instead of manually refining a complex prompt, create a process where an AI agent evaluates its own output. By providing a framework for self-critique, including quantitative scores and qualitative reasoning, the AI can iteratively enhance its own system instructions and achieve a much stronger result.
The process of building AI tools is becoming automated. Claude features a 'Skill Creator,' a skill that builds other skills from natural language prompts. This meta-capability allows users to generate custom AI workflows without writing code, essentially asking the AI to build the exact tool they need for a task.
A truly effective skill isn't created in one shot. The best practice is to treat the first version as a draft, then iteratively refine it through research, self-critique, and testing to make the AI "think like an expert, not just follow steps."
Instead of manually maintaining your AI's custom instructions, end work sessions by asking it, "What did you learn about working with me?" This turns the AI into a partner in its own optimization, creating a self-improving system.
A major flaw in current AI is that models are frozen after training and don't learn from new interactions. "Nested Learning," a new technique from Google, offers a path for models to continually update, mimicking a key aspect of human intelligence and overcoming this static limitation.
The perceived need for a new "continual learning" architecture is overstated. Current models can already achieve this functionally by building their own tools and apps based on new information. This reframes the challenge from a fundamental research problem to a practical prompt engineering and application design issue.
