Jenik: Accelerated Understanding has trained physics models up to 1-trillion parameters
Benedikt Jenik · Faster Chips That Don't Melt — Anima Anandkumar & Benedikt Jenik, Accelerated Understanding · Sep 4, 2026 · at 7:34
Benedikt Jenik, co-founder of Accelerated Understanding, details the scale of model training runs the startup has conducted.
0:00 / 0:07exact quote · 7.5s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“We've trained, done hundreds of training runs. We've trained up to a trillion parameter models. So we've really shown the stuff to take off.”
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 Benedikt Jenik
Jenik: Accelerated Understanding achieved 5-trillion token inference context length
“Like we're able to train up to a trillion context input. We're able to train With like, even inputs, outputs, both trillion context length, we are able to do inference at five trillion contexts.”
Jenik: PDE feedback pushes physics AI models to exceed training data
“You can use those PDEs both for numerical simulators to generate data, but if you're clever about it, you can even use them as a training signal. You can check how well is my model actually doing on the PDEs themselves. And use that as an additional training s…”
Jenik: Broadening PDE training domains solves the physical sim-to-real gap
“One interesting thing with PDEs is we are actually fairly confident, like the math is known, that when you solve a PDE correctly, you're doing the physics correctly. Like, obviously, you still need to make sure that you're representing the task that you're try…”
Jenik: A single 5-trillion-token model run generated 22 terabytes of output
“Like, for example, our five trillion run that we did, the outputs were 22 terabytes, and you want that kind of stuff in accelerator memory.”
Jenik: Traditional chip design loses performance by separating digital logic and physics
“Especially when you look at the chip design itself, it was much more a, let's start in the digital, let's freeze the digital in, let's send it through some physics for a one time check, like the PDK dictates, I have to have The following feature, otherwise TSN…”