Posts

Hayao Miyazaki is my favorite artist and director. Though I haven’t watched his entire filmography, every moment of the films I have seen captivates me. In “Spirited Away,” the dust ball creatures exemplify his artistic prowess—his ability to infuse life into the mundane through his drawings. His work is truly a labor of love. Every scene in his animated films is hand-drawn and painted with watercolor. To put this dedication in perspective: a single 4 second crowd scene from Studio Ghibli required 1 year and 3 months to complete. At 24 frames per second, that’s 96 images—roughly 6.4 images per month or one-third of an image in an eight-hour workday. At this rate, animators would spend a decade creating just 28.8 seconds of footage. This extraordinary commitment to craft has established Miyazaki’s work as iconic for decades. ...

When you want to look for user pain points, go to a bar in the middle of the week, look for the most desparate looking person and buy them a beer. They’d probably have something substantial to talk about. While I don’t usually go to bars during weekdays, I’ve found some similar ways of identifying user needs, mostly through conversations or online forums. This is a running document of the user needs or pain points that I’ve found to be interesting. Perhaps some of them will turn out to be viable business oppportunities. ...

2024 felt to have passed by very quickly, in part because I had interesting work to occupy my time. Early in the year, after expanding Cogno and gaining some traction, work slowly stalled: though we did code and talk to customers, the cycles were far and wide in between. The focus on multi-agent systems was (as of writing this) in the right direction, yet we did not find the niche to tackle sales conversion improvement. ...

Every now and then, I come across products or features, where the user action is probably not what the designer has envisioned. Some demonstrate the ingenuity of users, while others are less appropriate. Here’s a few that I’ve come across: 2024-11-26 Related search queries: For contrast, here’s a valid case:

Reflecting on my list of failed projects, very few failed due to lack of innovation. Since I began working with LLMs in fall 2022, there has been an abundance of interesting GenAI technologies to experiment with. It started with “domain specific prompting/finetuning” and data flywheels (thou not even now does anyone know what this looks like in action). By spring 2023, the focus shifted to LLMs as agents, exemplified by the Generative Agents paper, Microsoft AutoGen, and a few opensource projects like MetaGPT. At Cogno, we also built multi-agent systems, integrating various function calling features and agent collaboration for complex task reasoning. Everyone built, few created value (Glean focused on enterprise search, while Moveworks created value through api actions, neither of which I believe agents to have mattered). Founders encouraged each other’s enthusiasm, while investors rushed to learn the latest buzzwords in LLM technology (‘prompt engineering’ and ‘function calls’ sounded less sexy compared to’agents’). ...

It’s fascinating how differently our brains process audio and text. When we read, we’re essentially interacting with a graphical user interface - scanning, jumping between sections, processing information at our own pace. We’ve evolved sophisticated tools for text: highlighting, bookmarking, section headers, and search functions. Yet despite these advantages, text may at times feel less engaging than a good conversation. Speaking, in contrast, is inherently linear and social. There’s something about the human voice that keeps us present - the subtle shifts in tone, the natural pauses, the back-and-forth rhythm. It’s why we can stay engaged in a podcast while walking (and multitask), yet reading typically demands our full attention. ...

I never listen to recordings of myself talking, yet I love having conversations: while walking, at coffee shops, and even on podcasts. We are all familiar with the conversation format and can easily produce content, embodying our thoughts and ideas through spoken language. I believe we are at a moment where the way we interface with spoken language is about to change. Imagine having a graphical user interface for conversations. What would that look like? There wouldn’t be a physical embodiment, yet everything that makes conversations so natural could now be part of the podcast (or narrated video) experience. “What you said about Peet’s,” references, and grounding could now be conveyed in full. Instead of section headings, all the information could be presented in the appropriate format when needed. NotebookLM is an interesting concept, but is there an opportunity for a fundamentally new content format? ...

“Inspiration unlocks the future; technology will catch up.” This phrase, from one of my favorite directors, Hayao Miyazaki, appears in the animation “The Wind Rises” (though my favorite movie is “Princess Mononoke”). While it’s easy to get caught up in innovation (and the hype popular news outlets create alongside it), I still view technology as a tool for solving human problems. This may sound counterintuitive, yet most of us are still pretty bad at identifying our own needs and pains, leading to engineering feats with non-existent product-market fit prospects. Returning to the question of why I want to start writing again: I like the language medium; it forces you to express your ideas clearly. I anticipate mainly writing about products and the strange quirks that make us human, but may occasionally add in a few other things that interest me. I’ll try to keep these posts relatively short, both to make it manageable for myself and to keep it interesting for you. ...

Every now and then I like to read about the advice of others who’ve succeeded in their field. Here’s a few that I personally found to be enlightening and practical. Patrick Collison: Go deep on things. Become an expert. In particular, try to go deep on multiple things. (To varying degrees, I tried to go deep on languages, programming, writing, physics, math. Some of those stuck more than others.) One of the main things you should try to achieve by age 20 is some sense for which kinds of things you enjoy doing. This probably won’t change a lot throughout your life and so you should try to discover the shape of that space as quickly as you can. ...

This week, I wanted to organize my thoughts about AI-generated content (AIGC) and creativity-related products from the past few months. Rather than focusing solely on my own projects, I’d like to explore the foundational aspects of AI product design, interspersing examples from my recent work. First, I want to emphasize that technology is merely a tool intended to better serve business needs. If it doesn’t significantly improve efficiency, traditional methods may be more appropriate. Second, despite the many imaginative possibilities of current technology, applications should ultimately be guided by user needs. Finally, AI technologies and markets evolve rapidly, making predictions difficult to validate, but exploring content understanding and generation remains an intriguing challenge. ...