The boom from LLMs was a 'shortcut' that mined intelligence from existing human data. This has limits. To achieve novel breakthroughs beyond that corpus, the field now re-integrates the original DeepMind philosophy of agents learning through interaction (like reinforcement learning) to generate truly new knowledge.

The significant leap in LLMs isn't just better text generation, but their ability to autonomously execute complex, sequential tasks. This 'agentic behavior' allows them to handle multi-step processes like scientific validation workflows, a capability earlier models lacked, moving them beyond single-command execution.

The industry was surprised to learn that the tool-calling and problem-solving DNA of coding agents provides the necessary foundation for general-purpose agents. This was not the anticipated route to AGI, which labs hadn't explicitly trained for, yet it has become the dominant and most promising approach.

AI platforms using the same base model (e.g., Claude) can produce vastly different results. The key differentiator is the proprietary 'agent' layer built on top, which gives the model specific tools to interact with code (read, write, edit files). A superior agent leads to superior performance.

Modern AI systems can now 'speed run' a digital version of evolution. By combining an LLM's ability to rapidly generate hypotheses with an automated evaluation function, these systems can test ideas, discard failures, and pursue successful 'lineages' at a pace far exceeding biological evolution.

The term 'vibe coding,' once used to describe AI-assisted development, is now obsolete. The industry has matured to complex, multi-agent systems where AIs coordinate, write, test, and resolve issues across codebases with little human intervention. This signals a new era of 'agentic engineering' that is far more sophisticated than simple prompting.

Effectively using AI for a complex coding project required creating a spec-driven test framework. This provided the AI agent a 'fixed point' (passing tests) to iterate towards, enabling it to self-correct and autonomously verify the correctness of its output in a successful feedback loop.

Complex AI development uses a pool of specialized agents. Like ants building a hill, some are workers, some are managers, and some review and discard bad code. This collaborative, layered system produces emergent results without a single orchestrator.

Biological evolution used meta-reinforcement learning to create agents that could then perform imitation learning. The current AI paradigm is inverted: it starts with pure imitation learners (base LLMs) and then attempts to graft reinforcement learning on top to create coherent agency and goals. The success of this biologically 'backwards' approach remains an open question.