@Modular: People ask what our secret is when they see our performance numbers. Brendan Hansknecht, AI Performance Engineering Man…
Summary
Brendan Hansknecht from Modular explains that their high performance numbers stem from treating performance as a full-stack problem, rather than relying on piecemeal components in production.
View Cached Full Text
Cached at: 09/04/26, 12:19 AM
People ask what our secret is when they see our performance numbers.
Brendan Hansknecht, AI Performance Engineering Manager, on why performance is a full-stack problem, and why gluing together someone else’s kernels, tokenizers, and schedulers doesn’t work in production:
@Modular: People ask what our secret is when they see our performance numbers. Brendan Hansknecht, AI Performance Engineering Man…
Channel: @Modular Source: https://www.youtube.com/watch?v=J_ezNJ6eyHk
Similar Articles
@AMD: From bring-up to tuning, AMD and @OpenAI engineers are sharing insights to push performance further. Go behind the coll…
AMD and OpenAI engineers collaborate to share insights on performance optimization, featuring a behind-the-scenes look with OpenAI's VP of Compute Strategy, Sachin Katti.
30 to 70 PRs a Day: How We Managed to Not Wreck Our Systems
Honeycomb's engineering team more than doubled peak daily merges from ~30 to ~74 using AI tools like Claude Code, with AI-attributed code rising to 82.6% by June 2026, while managing incidents proportionally. They share practices like continuous delivery, fast CI, and observability that amplified with AI.
@AMD: Choosing the right model is only part of the conversation. Hear @AnthropicAI's Head of Claude Code, Boris Cherny (@BChe…
Anthropic's Head of Claude Code, Boris Cherny, discusses the evolution from autocomplete to autonomous agents and how Claude has boosted developer output by 8x across the company, emphasizing workflow redesign over model choice.
@russelljkaplan: I don't think people realize how different programming feels when proactive automations are set up. On every important …
A Cognition employee describes how Devin automations monitor Slack channels, triaging and solving issues autonomously, making engineering progress almost entirely autonomous while engineers focus on big bets.
@poteto: https://x.com/poteto/status/2069824386283319343
The article draws parallels between managing engineering teams and managing AI agents, using Andy Grove's management principles to build reliable agent loops, illustrated through a performance debugging case study at Cursor.