The Drum · Weekly AI news, freeSubscribe →
4 notes
Long-form writing on engineering and leadership from the founder. These are genuine authored pieces — personal perspective on building, scaling, and leading in the AI era, distinct from the weekly news digest.
The real economics of a production LLM pipeline: resumability, cost-aware routing, and measuring when local beats the API
Running your LLM pipeline locally to save money is mostly a myth: at real scale, batched cloud inference is pocket change. The engineering that matters is resumability, cost-aware routing, and a benchmark that measures your own local-versus-cloud crossover instead of inheriting a headline.
Jul 2026
9 min read
Who's the authority now? Leading in the age of the jagged generalist
AI is a jagged specialist: brilliant on one task, confidently wrong on the next. So the authority in the room is no longer whoever knows most, but whoever knows where the machine can be trusted.
Jul 2026
7 min read
Stop shipping AI agents you can't measure: evals + observability from scratch
Everyone can build an AI agent. Almost nobody can prove it still works after the next prompt tweak or model bump. This is the smallest vendor-neutral way to make an agent's accuracy a CI gate, so a behavioural regression fails the build like a broken test.
Jul 2026
6 min read
The psychological cost of AI is a leadership choice, not a technology outcome
AI adoption measurably harms wellbeing at work, yet the evidence shows leadership behaviour buffers the damage. The human cost is a choice, not a side-effect of the technology.
Jul 2026
7 min read
© 2026 Cedar & Bloom. All rights reserved.
