Tag: insights

Categories
AI: Large Language Models AI: Prompting Photography

Creative Image Analysis with an LLM Partner

I came across a fun experiment being done by Mitchell Lensink which he shares on one of his blogs.

He takes one of his photos, feeds it into one of the AI large language models and asks the LLM to produce a detailed description of the photo. He then continues by asking the model to create a new image based upon the description it produced as part of its analysis.

I tried this out on a few of my images and enjoyed seeing the results. Here’s an example…

Prompt (taken from one of his examples): Please describe the attached image as well as you can. Don’t skimp out on details and make sure you will be able to understand what’s in the image when you read the description. You need to be able to form a mental picture of the image, without actually seeing it.

Here’s what Google Gemini 2.0 Flash produced:

Imagine a serene lake bathed in the warm glow of either sunrise or sunset. The sun, positioned towards the upper left of the frame, casts a brilliant light that flares slightly around the edges of the tall trees lining the left bank. These trees are silhouetted against the bright sky, their dark shapes contrasting sharply with the golden light.
The lake itself occupies the majority of the frame, its surface reflecting the sky and the surrounding trees like a mirror. Gentle ripples disturb the otherwise smooth surface, creating subtle patterns of light and shadow. In the middle of the lake, a fountain sends a spray of water upwards, catching the light and adding a dynamic element to the tranquil scene.
The far bank of the lake is also lined with mature trees, their foliage appearing lush and green where the light touches them, and darker in the shadows. A low wooden fence runs along a portion of this bank, suggesting a pathway or boundary.
In the foreground, along the near edge of the lake, there’s a patch of vibrant green grasses interspersed with delicate white and yellow flowers. These plants are in sharp focus, drawing the viewer’s eye into the scene and adding a touch of natural beauty in the immediate foreground.
The overall atmosphere is peaceful and picturesque, a moment captured in time where the natural elements – water, trees, light, and flora – come together in a harmonious and visually appealing way. The air likely feels still and the sounds would probably be soft – perhaps the gentle splashing of the fountain or the rustling of leaves.

Wow! That’s a description that goes well beyond anything I might have written to describe my photograph! Lots of details and new insights that help us see more deeply into what’s in that image.

And here’s the next step – the image it produced when I asked it to create a new one based on the description above:

That’s a very different image but I can see how it got there!

This little experiment is worth playing with some more I think!

Categories
Living

Serendipity vs Cynicism

This morning I’m listening to the latest edition of the Focused podcast hosted by Mike Schmitz and David Sparks. They’re interviewing the author of the new book “Tiny Experiments” by Anne-Laure Le Cunff. I’ve been a subscriber to her Ness Labs newsletter and am enjoying listening to their conversation.

One of the things she talks about is how she’s been thinking about what’s the inverse of living life with tiny experiments. She settled on, among other things, cynicism. Wow, that resonates with me!

As I got older, I came to appreciate the real value that serendipity plays in my life. That’s what leads to new experiences, tiny experiments, new understandings, etc. The opposite often is cynicism. Cynics resist change. They critique others – especially when they’re pursuing new things that the cynic finds meaningless.

I’ve come to really listen to what happens with serendipity. How it unlocks new insights, new learnings, often leading to new tiny experiments which open even more new vistas. For me, that’s what living is all about.

Categories
AI AI: Large Language Models Claude

Make It Better

I came across a post on X this morning with some advice I immediately tried out. The advice – when working with an AI to help create writing or code – is to reply to the first pass the AI takes by asking it to “make it better”. The author suggested doing this multiple times.

I tried this out with Claude and enjoyed how it worked on just the first “make it better” pass. When I asked it to “make it better” it began by replying:

Certainly, I’ll refine the musing to make it more impactful and engaging. I’ll focus on enhancing the imagery, tightening the structure, and deepening the insights.

And indeed the second “better” pass that it wrote was even better. A fun experiment to try on your next use of an AI chatbot.

Categories
AI Leadership

The Power of Two

I recently watched and thoroughly enjoyed Harry Stebbings’ interview with OpenAI’s Sam Altman (CEO) and Brad Lightcap (COO). In addition to gaining new insights into OpenAI’s evolution, their conversation covered a wide range of topics regarding the future of AI and its implications for society and new ventures.

One of the most fascinating aspects was the dynamic between Altman and Lightcap — hearing them discuss their respective strengths, weaknesses, and how those translate into their roles at OpenAI. It’s uncommon to witness a dual interview like this, with two colleagues who have clearly worked together for years and have complete confidence and trust in each other’s judgment and insights.

Throughout my involvement with various small companies, I wish I could have experienced such a powerful duo! In my experience, it’s not uncommon for the CEO to dominate the senior management team’s dynamics. While this sometimes works well, I’ve also seen it lead to reduced performance or frustration among senior managers due to the CEO’s actions.

Altman and Lightcap (and OpenAI by extension) appear to have a much more synergistic working relationship — effectively amounting to a co-equal division of responsibilities. I highly recommend watching this conversation for anyone involved in a startup aiming to scale quickly and effectively! Congratulations to Harry Stebbings for his hosting this excellent conversation with two key individuals leading the evolution of AI!

Categories
Creativity Tools Writing

The Untamed Genius of Not Thinking: Bradbury, Creativity and the Two Minds

“Don’t think.” At first glance, Ray Bradbury’s famous advice on the creative act seems almost heretical. How can we create anything of substance, anything brilliant and transcendent, without deep cognitive focus and analytical thinking?

And yet, there is profound wisdom in Bradbury’s deceptively simple directive when we consider what true creativity demands – a willingness to surrender to the uncharted waters of the unconscious mind, to temporarily disengage from the constraints of pure rationality, and allow the kaleidoscopic shards of our imagination to swirl and coalesce into novel, unorthodox forms.

For Bradbury’s “Don’t think” is not advocating mindlessness, but rather a state of expansive awareness, a openness to the unbridled torrent of insights, images and ideas that bubble up from the our mind’s depths when we stop trying to consciously control and direct the creative flow. It is the practiced meditation of clearing one’s mind to simply observe thoughts, associations and impressions to let them arise and fall away without judgement.

What Bradbury observed is that the act of conscious, analytical thinking, while critical for problem-solving, can actually impede the creative process. It tends to force us into our pre-existing neural pathways, compelling us to tread the well-worn grooves of prior patterns, making linear associations along very predictable lines. Creativity, on the other hand, beckons us into the wild underbrush of our minds, off the beaten path, into uncharted realms where we can be liberated from our self-imposed boundaries.

There’s a connection between Bradbury’s advice and the concepts of right brain vs. left brain thinking. The left hemisphere is the seat of our logical, sequential, linguistic reasoning – the part of our mind that categorizes, defines, organizes and scrutinizes details. Our right brain, in contrast, is the hub of intuition, holistic perception, innovation and making new associations between disparate concepts.

When Bradbury said “Don’t think,” he was advocating taking a temporary pause from our left-brain dominance to allow the ingenious talents of our right brain to take primacy – to let it make unexpected leaps of creative fancy, to perceive reality from new angles, to connect ideas through metaphor and visual imagery rather than getting bogged down in deep analytical scrutiny. To let it just jam.

Our left brain’s vital role is not eliminated, of course. Both hemispheres ultimately work in concert. But for tapping into a more creative flow, giving the reins to the right brain’s propensity for unrestrained imagination and divergent thinking can open up new spheres of inspiration, unconstrained by us overthinking analytically.

From this space of simply allowing our mind to widely wander and make new neural associations, true creative breakthroughs are often born. As Bradbury knew, sometimes the greatest innovative genius emerges not from perspiration and analytical rigor, but from setting aside focused thought altogether and trusting the untamed wisdom of the unconscious, innovative mind. Taking a break and going for a walk outside has a way of helping open up that process, lifting our mood and opening us up to new insights and connections.

“Don’t think” is a refreshing perspective on the richness of human cognition. It recognizes the vital role of holistic, nonlinear and imaginative modes of processing – aspects of our mindful intelligence often overshadowed by our pure left-brain rationality. Bradbury’s imperative frees us to fully embrace the kaleidoscopic potency of our creative right minds.