‘The rise of public cloud transformed enterprise software. Today, virtually every large organization has a cloud engineering team, and almost every digital experience relies on cloud infrastructure behind the scenes.

AI is likely to follow a similar trajectory but much faster.
In the coming years, every enterprise will likely have dedicated AI engineering teams. Eventually, those teams may become larger and more strategically important than traditional cloud engineering teams, with cloud infrastructure serving as the foundation that enables AI rather than being the primary focus itself.

The applications built on top of AI will also evolve far beyond today’s chat interfaces. Just as cloud computing moved us from installing software locally to streaming media, collaborating in real time, and delivering rich web applications, AI will reshape how humans interact with software.

The future won’t simply be typing prompts into a chatbot. AI systems will increasingly respond to multimodal inputs like your voice, facial expressions, gaze, gestures and potentially other biometric signals that will create interfaces that feel far more natural and adaptive than today’s button-driven applications.
Websites filled with menus and buttons will increasingly resemble legacy systems. The next generation of software will revolve around intelligent interaction rather than graphical interfaces.

Cloud computing took roughly two decades to become ubiquitous. AI appears to be compressing that timeline dramatically, suggesting that the transition to AI-native applications could happen far faster than the cloud revolution itself.’

Thoughts inspired by Corey Sanders on The PracticalAIShow discussing the Future of AI Infrastructure

The way humans interact with software is about to change dramatically. Instead of navigating menus and clicking buttons, we’ll increasingly interact directly with AI models using natural language. The future of software is shifting from button-driven interfaces to intelligent conversation.

‘One of the most valuable human qualities in the age of AI is our ability to ask questions that challenge the status quo.
Today’s AI is built on deep learning. Learning from what already exists and generating remarkable new outputs from those patterns. But genuine progress still depends on people who are curious enough to question existing assumptions, imagine alternatives, and ask, “What if there’s a better way?”

As AI becomes more capable, our responsibility isn’t to stop thinking…it’s to think more deeply. We should cultivate curiosity,challenge conventional wisdom and never lose the habit of asking difficult questions. That mindset will drive not only the future of AI, but every major technological innovation that follows.’

Thoughts inspired by Corey Sanders, SVP of Product at CoreWeave on the ‘Practical AI Show’

As datasets explode to tens of trillions of tokens, the classic 80/20 split is dead. Now it’s common to see 99%+ for training, with just 0.5% each for dev and test. Even half a percent of 15 trillion tokens still gives you billions of examples. Bigger data completely changes the math.

‘One of the biggest frustrations with LLMs is typing. By the time you’ve finished writing a prompt, you’re already mentally drained. Speaking is a completely different experience. You can simply let your thoughts flow for a minute or two, and LLMs are remarkably good at understanding and organizing that raw stream of consciousness. It has completely changed the way I use AI and honestly, it’s changed everything for me.’

Thoughts from Jason on the All-In podcast

♟️ Modern chess engines can evaluate 10–50 million positions per second after every move.
The human mind simply cannot compete with that level of strategic calculation over the board.

For years, many have argued that healthcare has been approaching a breaking point. Today, for the first time, there is genuine reason for optimism. AI offers a path to doing more with less, easing the burden on clinicians and nurses while making their work more fulfilling. It also has the potential to transform the patient experience—reducing confusion, frustration, and despair. In many ways, this is an extraordinary time to be working in healthcare. ❤️

‘Software engineering is evolving in the AI era. The role is no longer just about writing code. Increasingly, the highest-value skills are long-term systems thinking, making architectural decisions that stand the test of time, developing a deep understanding of customers and domain experts to gather exceptional requirements, and leveraging AI to preserve organizational knowledge so new employees can quickly build on past decisions instead of starting from scratch.

The companies that thrive won’t simply use AI—they’ll rethink how they build products and organize themselves from the ground up for an AI-first world.’

Nikhil Buduma, CEO and cofounder of Ambience Healthcare discussing deployment of AI in Healthcare on a16z show.

‘Closing the gap with the leading frontier models isn’t just about incremental improvements.Three factors appear to matter most: model architecture, active parameter count, and the quality/scale of training data. While many open and international models continue to improve rapidly, the frontier remains highly competitive, with progress accelerating across the industry.

The pace of AI development is extraordinary, and the gap between leading models and challengers can narrow surprisingly quickly.’

Thoughts from Alistair Pullen, CEO and co-founder of Cosine on MLStreetTalk discussing the importance of a nation maintaining it digital sovereignty in the Age of Artificial Intelligence

‘We have a huge problem with benchmarks in machine learning. So we are obsessed with passing benchmarks but neglect reliability,consistency, security and abstraction forming. This is one of the most important and under-discussed problems in machine learning right now.’

- Dr. Tim Scarfe

Journal Entry
2026/07/13

Recently, I’ve been noticing 11:11 quite often, usually when I least expect it. Whenever I see it, I close my eyes, say the Lord’s Prayer, and give thanks for the many blessings in my life.
Whether it’s coincidence or simply a gentle reminder to pause, I appreciate the moment to reflect with gratitude.