Taskaya: Model architectures will keep churning due to researcher novelty bias
Batuhan Taskaya · A Technical History of Generative Media · Sep 8, 2025 · at 27:10
Batuhan Taskaya, co-founder of Fal, discusses why multimodal diffusion architectures (like MMDiT vs. single-stream DiT) keep shifting across frontier AI labs.
0:00 / 0:07exact quote · 7.7s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“I think the architecture is going to keep changing until this, like, paradigm of, like, you know, researchers changing stuff for the sake of changing, you know, finishes.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Batuhan Taskaya
Taskaya: Flux was the first enterprise-ready generative image model
“The team at Stability left to start Black Forest Labs, which released Flux models. And that was the first model to, you know, breach the barrier of commercially usable, you know, enterprise-ready grade models”
Taskaya: Custom ASICs do not make sense given low Nvidia GEMM overhead
“What is the overhead of an NVIDIA GAM instruction, right? It's like 16%. So like you're essentially buying a, Matrix multiplication machine. So, like, it doesn't really make sense to specialize it that much.”
Taskaya: NSFW content makes up less than 1% of Fal traffic
“Moderation is optional to a level where, like, illegal content is moderated, and we also track, like, the non-illegal content NSFW moderation, and, like, we haven't seen, like, we haven't seen more than one percent.”
Taskaya: 80% of promotional video content will be AI-generated within 12 months
“Like 12 months, I think like 80% of this is going to be generated.”
Taskaya: Training a state-of-the-art image model costs under $1M
“Like right now, like if you look, if you want to train a Sota image model, I don't think it's going to cost more than a million dollars. It's extremely cheap. It's like a matter of data engineering effort, cleaning. It's, I think it's a function of data set.”