The brain's hardware limitations, like slow and stochastic neurons, may actually be advantages. These properties seem perfectly suited for probabilistic inference algorithms that rely on sampling—a task that requires explicit, computationally-intensive random number generation in digital systems. Hardware and algorithm are likely co-designed.

The hardware for advanced robotics has existed for decades, but the intelligence to power it was prohibitively expensive. With the advent of cheap, powerful AI models, the final barrier has been removed, unleashing a rapid explosion in robotics innovation.

Over two-thirds of reasoning models' performance gains came from massively increasing their 'thinking time' (inference scaling). This was a one-time jump from a zero baseline. Further gains are prohibitively expensive due to compute limitations, meaning this is not a repeatable source of progress.

Today's AI boom is fueled by scaling computation, which is a known engineering challenge. The alternative, embedding nuanced, human-like inductive biases, is far harder as it requires a deep understanding of the problem space. This difficulty gap explains why massive models dominate AI development over more targeted, efficient ones—scaling is simply the more straightforward path.

We are building AI, a fundamentally stochastic and fuzzy system, on top of highly precise and deterministic digital computers. Unconventional AI founder Naveen Rao argues this is a profound mismatch. The goal is to build a new computing substrate—analog circuits—that is isomorphic to the nature of intelligence itself.

The "bitter lesson" in AI research posits that methods leveraging massive computation scale better and ultimately win out over approaches that rely on human-designed domain knowledge or clever shortcuts, favoring scale over ingenuity.

AI progress was expected to stall in 2024-2025 due to hardware limitations on pre-training scaling laws. However, breakthroughs in post-training techniques like reasoning and test-time compute provided a new vector for improvement, bridging the gap until next-generation chips like NVIDIA's Blackwell arrived.

The shift from simple query-based AI to agentic AI, where AI calls itself recursively to solve complex tasks, increases compute demand by orders of magnitude. Most people, especially non-coders, fail to grasp this exponential shift, leading them to consistently underestimate the scale and duration of the AI infrastructure build-out.

The current AI boom isn't a sudden, dangerous phenomenon. It's the culmination of 80 years of research since the first neural network paper in 1943. This long, steady progress counters the recent media-fueled hysteria about AI's immediate dangers.