analiza aiqbench
The article presents empirical data from 40 trillion tokens of usage to challenge the industry's focus on model benchmarks, arguing instead that successful AI agent adoption hinges on trust and practical engineering workflows. It identifies specific failure points in context construction and multi-model routing that are critical for scaling agentic systems beyond theoretical capabilities. This analysis offers a grounded perspective on the gap between marketing narratives and the realities of developer integration.
Presentation: What 25 Trillion Tokens Reveal About How Developers Actually Adopt AI Agents
Brendan O'Leary discusses how real-world AI adoption depends on building trust rather than chasing model benchmarks. Drawing from 40 trillion tokens of usage data, he explains the four rungs of the AI adoption ladder and analyzes key failure points in context construction, multi-model routing, and feedback loops to help engineering leaders successfully scale agentic workflows. By Brendan O’Leary
Brendan O'Leary: My name is Brendan O'Leary. I'm a founding developer relations engineer at Kilo Code. How many people have heard of Kilo Code? That's key, because I'm about to present you a whole bunch of our data. If you don't know who we are, not really helpful. How many have heard of Codex or Claude Code, or OpenCode maybe? What Kilo Code is, is an open-source agentic engineering tool. You can think of it as like a Claude Code or a Cursor, but it's open source. We have surfaces in the CLI, like a Claude Code or a Codex. We have surfaces inside of VS Code, so like a VS Code extension. You can think of like a Cline, or maybe like a Cursor, if Cursor is a fork of VS Code, in some ways you can think of it the same way. Then we also have cloud agents. The only point in telling you all that is like, where does all this data come from? It's all real-world data from our gateway. We'll talk a little bit more about the specifics of the data. Being that I'm at Kilo, and we're this open-source competitor in this highly competitive…
Extras afișat conform termenilor RSS ai publicației · 200 cuvinte · textul integral și figurile sunt pe site-ul publicației
Subiecte conexe
Research Note: Filtering Subversion-Relevant Information From Pretraining Data Is Feasible
LessWrong · 5 oct. 2026
Presentation: You Can't Trust Your AI Bill. And Neither Can I
InfoQ · 12 oct. 2026
Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI
Latent Space · 21 sept. 2026
The Case Against Slowing Down AI
LessWrong · 29 sept. 2026