been doing this the last few weeks but highly recommend doing it locally or with a privacy preserving service like tinfoil or venice, for the sake of others in your logs and also because most people don’t speak candidly to claude. talking to a private ai feels as safe as thinking
@genekogan
-
Most choose capability or safety, not both
By
–
It doesn’t seem like many people work on capability and safety at the same time. I kind of think most people understand they are not the difference maker on whether the consequences turn out good or bad. If they genuinely think it’s the latter, they stop working on capability.
-
Disco hall recreation in Three.js switched to Opus over safety filter
By
–
My first task for Fable was to recreate a disco hall from a photo using Three.js. It worked for 15 minutes before switching to Opus because of a safety filter, which felt a bit odd. Did a great job though. Artifact: https://
claude.ai/public/artifac
ts/a74fbb2a-a31a-4221-a695-b39266b419fd
… -
Curiosity about Anthropic’s promotional image creation
By
–
I am curious how Anthropic makes images for their promotional materials. Is it just Claude collaging found images? It doesn't look like an image model. https://t.co/SAaqUUkxNA
— Gene Kogan (@genekogan) 9 juin 2026I am curious how Anthropic creates images for its promotional materials. Is it simply Claude assembling found images? That doesn't look like an image model.
-
Runway’s Aleph 2.0 excels at digital/cartoon face swaps.
By
–
Runway's Aleph 2.0 works really well on swapping in digital/cartoon faces. This was always tricky for me. pic.twitter.com/2tBWtx3HZA
— Gene Kogan (@genekogan) 6 juin 2026Runway's Aleph 2.0 works really well on swapping in digital/cartoon faces. This was always tricky for me.
-
Genekogan workshop on coding agents for music and art at Vibecon
By
–
Very excited to be giving a workshop at @Replit
's Vibecon on June 17 in NYC. I'll be sharing techniques for getting coding agents to make music and art. -
On-chain GANs: InChainPepeGAN, Concrete, and AAA improvements
By
–
I stand corrected! There are at least two on-chain GANs that predate this, InChainPepeGAN (from 2023!) and Concrete by Higgs by @0xdiid
. So AAA is not first in that regard, although it's still innovative, as it generates clear subjects in high res, so it pushes fidelity forward -
Question about GAN sampling via contract
By
–
GAN sampled through contract? definitely possible I missed something, but I've never seen that. I'd be curious for references
-
10-year milestone for a real-time AI installation
By
–
This also marks 10 years of Cubist Mirror, my first real-time AI installation.
— Gene Kogan (@genekogan) 21 mai 2026
At 360 pixels x 1 fps, it's no stream diffusion, but 6 months before then, I could only make 1 frame every 15 minutes.https://t.co/DrxlOJZGhdThis also marks 10 years of Cubist Mirror, my first real-time AI installation. At 360 pixels x 1 fps, it's no stream diffusion, but 6 months before then, I could only make 1 frame every 15 minutes.
-
How Coding Agents Perceive Your Appearance
By
–
What you look like to your coding agents. pic.twitter.com/QyTyLEzYOe
— Gene Kogan (@genekogan) 28 avril 2026What you look like to your coding agents.