Finding new challenges after decades of engineering
Much as I talk about how the current generation of AI tooling is missing the point, and it is, I still think the technology is incredible.
Lynn Cole / 标签
art process
A thread through the work.
Warp paintings, ControlNet, and a little film
Two hand-made warp paintings, a ControlNet layer, thirty renders and FILM became a short visual experiment.
Your Prompt Filter Isn’t Keeping Anyone Safe
Prompt moderation is not image moderation. I argue for evaluating generated images and building correction loops around the output.
What AI makes possible for independent builders
AI criticism goes in cycles, where the same people repeat the same arguments like they thought of them.
Underpaint and a collaborative painting room
Underpaint combines inpainting, outpainting, prompting, detailing and refinement with a plan for collaborative painting sessions.
Context shaping is an engineering skill
Context shaping is more than delegation: iteration, problem solving, manual rewrites and interfaces designed around people.
Evaluating a long-horizon solver with Pizza Empire
Pizza Empire tests a long-horizon coding swarm against a whole product: ordering, kitchen workflow, delivery and the constraints that make them coherent.
Underpaint’s document-scoped prompt memory
Underpaint’s Proompt Manager keeps reusable prompts within the scope of a document, tying the painting workflow to its existing session history.
Predictions for 2026, written in December 2025
My predictions for 2026, written in December 2025: small models, edge compute, changing tooling, creative technology and the structures of power.
We have had the vibe-coding argument before
We have heard the vibe-coding argument before—in digital art, visual programming, web design, music and animation. Lowering the barrier changes who gets to try.
Voice, multimodality, and lessons from a weekend build
Weekend lessons from voice, multimodal inference, certainty scoring, image stacks and tool instructions trained into small LoRAs.
Learning engineering through AI-assisted generation
Learning with AI-assisted generation can be a way into engineering. Build, question the output, document the process and discover what better means.
What noise painting is trying to do
Noise painting uses hand-crafted adversarial inputs and incongruent prompts to push diffusion into unexpected visual territory.
Kinetic Painter: getting latency out of the way
A conversation with Jev has me thinking about returning to Kinetic Painter.
So how does underpainting work?
Underpainting turns outpainting inward: segmentation supplies the pieces, visual reasoning makes judgments, and diffusion reconstructs what belongs underneath.
A noise-painting pipeline, from painted input to refinement
The idea is that you start with a hand painted image or collage, but that you design it in such a way as that it messes up the classification and denoising systems in a diffusion model.
Recognizing my signature in Flux
Recognizing my signature in Flux got me thinking about training, adversarial art and the influence artists leave inside models.
Fixing the planning loop before the next benchmark run
A new planning loop helped the coding swarm, then conflicting tickets melted the benchmark. The next fix is backlog validation before implementation.
Becoming an AI generalist in public
Being an AI generalist was not always a comfortable professional identity. Computer vision and agents remain some of the most creatively satisfying engineering work I do.
Digital painting needs to get its hands dirty
I want digital painting to feel less sanitary: a canvas driven by hand movements, voice commands and a game engine, where the colors can finally get their hands dirty.