Insight certainty 4/5 debate potential 2/5

Bubna: Production AI agents require specialized sandboxes for compute and networking control

Akshat Bubna · The Future of AI Infra: from Kubernetes to Agent Sandboxes — Akshat Bubna, Modal CTO · Jul 8, 2026 · at 46:05

Modal CTO Akshat Bubna explains why managed agent platforms from foundation labs are insufficient for production applications compared to specialized sandboxes.

0:00 / 0:24exact quote · 24.9s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“You need a lot more control over your compute primitive on things like what sort of, how do you persist different files that the agent has access to, and how do you snapshot and restore? How do you control the networking? Maybe you want GPUs. When you get to that point, you kind of want A specialized sandbox provider that gives you those things, and that's the role that we are trying to play.”

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 Akshat Bubna

Insight
Bubna: Speculative decoding accept length delivers multiplicative speedups over kernel tuning
“People talk a lot about, we made these kernels faster and whatnot, but improving kernel only give you like a few percentage points of improvement and increasing except length literally is a multiplicative decrease.”
Akshat Bubna Jul 8, 2026 ▶ 18:48 The Future of AI Infra: from Kubernetes to Agent Sandboxes — Akshat Bubna, Modal CTO
Opinion
Bubna: Kubernetes lacks burstiness support and has terrible developer experience
“Kubernetes is hard to manage. It's not built for burstiness and custom images and has a terrible developer experience.”
Akshat Bubna Jul 8, 2026 ▶ 2:12 The Future of AI Infra: from Kubernetes to Agent Sandboxes — Akshat Bubna, Modal CTO
Opinion
Bubna: System Observability Is Becoming More Important Than Reading Code
“You still need humans to go interpret what's going on and you know, make judgment calls and whatnot. And that's, I feel like maybe more important now than looking at the code itself.”
Akshat Bubna Jul 8, 2026 ▶ 7:07 The Future of AI Infra: from Kubernetes to Agent Sandboxes — Akshat Bubna, Modal CTO
Assertion Supported
Bubna: Open-source DFlash matches proprietary speculative decoding performance
“Recently we shared our work on dflash, which is a block-based speculator, and we've open sourced all of it, so you can get, by using open source dflash, you can get the same performance as you would with one of the proprietary providers.”
Akshat Bubna Jul 8, 2026 ▶ 17:13 The Future of AI Infra: from Kubernetes to Agent Sandboxes — Akshat Bubna, Modal CTO
Opinion
Bubna: Sandboxes Require Hard Boundaries, Not LLM-Mediated Permissions
“I'm skeptical of LLM-mediated permissions for stuff that is At the sandbox level, because you do want hard boundaries. Otherwise, obviously someone can exfiltrate stuff.”
Akshat Bubna Jul 8, 2026 ▶ 44:21 The Future of AI Infra: from Kubernetes to Agent Sandboxes — Akshat Bubna, Modal CTO
Insight
Bubna: Model APIs primarily serve a less sticky hobbyist market
“This is one thing we've kind of stayed away from is providing an API for models, because I think providing Model APIs is, some of it ends up serving like a really hobbyist market, which is much less sticky.”
Akshat Bubna Jul 8, 2026 ▶ 49:49 The Future of AI Infra: from Kubernetes to Agent Sandboxes — Akshat Bubna, Modal CTO
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.