Agents quickly become outdated. To manage this lifecycle, build specific 'upgrade skills' that facilitate migration to new models. For larger-scale management, deploy 'meta-agents' whose sole job is to monitor other agents, identify outdated ones, and trigger the upgrade process.

Integrating the latest foundation model is complex because new models can break prompt tuning built around the quirks of older versions. Serval has found that a new model's unpredictability can outweigh its intelligence, sometimes forcing them to downgrade to an older, more reliable model to ensure consistent behavior.

Treat your AI skills and loops like code by managing them in Git. This provides a crucial safety net, allowing you to instantly roll back to a previously effective version if a new LLM update causes performance to decline.

Rather than achieving general intelligence through abstract reasoning, AI models improve by repeatedly identifying specific failures (like trick questions) and adding those scenarios into new training rounds. This "patching" approach, though seemingly inefficient, proved successful for self-driving cars and may be a viable path for language models.

Expect your AI agent's skills to fail initially. Treat each failure as a learning opportunity. Work with the agent to identify and fix the error, then instruct it to update the original skill file with the solution. This recursive process makes the skill more robust over time.

When AI labs release new models, they may de-prioritize certain skills like writing to focus on others like agentic capabilities. This causes noticeable shifts in tone and quality, forcing users to re-evaluate and adjust their custom instructions for GPTs and other AI tools.

Fable, a new frontier model, has built-in safety mechanisms. When asked to perform restricted tasks like accessing production databases or conducting machine learning research, it doesn't just refuse. Instead, it "drops" to the less capable Opus 4.8 model to handle the query, a process called nerfing.

Brown avoids manually editing text-based skill files, which can be brittle and model-dependent. Instead, he refines his AI's performance by providing direct, outcome-based verbal feedback, such as, "You didn't do a good job. Change the skill so you don't do that again."

When an AI model makes the same undesirable output two or three times, treat it as a signal. Create a custom rule or prompt instruction that explicitly codifies the desired behavior. This trains the AI to avoid that specific mistake in the future, improving consistency over time.