NEWS · CODING · #2037
Kilo Code presents large-token dataset on how developers adopt AI agents (25T cited)
At QCon AI, Brendan O'Leary of Kilo Code used real-world gateway usage data — the talk's title cites 25 trillion tokens while he also references ~40 trillion tokens — to argue developer adoption of agentic tools depends more on building trust than on model benchmark scores. He outlined a four-rung "trust ladder" and identified technical failure points in context construction, multi-model routing, and feedback loops that hinder scaling agentic workflows.
KEY POINTS
- At QCon AI, Brendan O'Leary of Kilo Code used real-world gateway usage data — the talk's title cites 25 trillion tokens while he also references ~40 trillion tokens — to argue developer adoption of agentic tools depends more on building trust than on model benchmark scores.
- He outlined a four-rung "trust ladder" and identified technical failure points in context construction, multi-model routing, and feedback loops that hinder scaling agentic workflows.
- Real-world, large-scale usage data showing adoption barriers and failure modes helps engineering leaders prioritize trust-building, context design, and routing strategies over chasing marginal benchmark gains.
WHY IT MATTERS
Real-world, large-scale usage data showing adoption barriers and failure modes helps engineering leaders prioritize trust-building, context design, and routing strategies over chasing marginal benchmark gains.