Cost-modeling AI workloads with FinOps eyes
The per-token price is the easy line. Everything else, the retries, the context overhead, the agentic tool calls, the egress, the GPU reservation underneath the API, is where the actual bill comes from.
Exploring the echoes reverberating through time left by the technology of yesterday as we embrace the technology of tomorrow.
Local-first AI: when does it actually beat the cloud?
The case for running AI locally is louder than the math justifies for most workloads. Worth being explicit about which workloads it actually wins, and which ones the cloud still owns.
Prompt engineering is dying. Prompt architecting isn't.
The job of crafting clever prompts to coax better answers from a frontier model is mostly over. The job of designing how prompts compose into systems is just beginning.
Three things AWS Bedrock still gets wrong
Bedrock has gotten meaningfully better in the last six months. The places it hasn't are still the same places. Worth being explicit about which gaps are likely to close and which look structural.
Self-hosted vector DB shootout: pgvector, Qdrant, LanceDB
Three open-source vector stores cover most of the self-hosted RAG surface area in 2025. Worth being concrete about which one fits which workload, because the trade-offs matter and the docs won't tell you.
MCP momentum: every major vendor has shipped one
Six months ago MCP was Anthropic's protocol nobody had implemented. Now it's a category every major vendor ships against. The thing nobody is asking is what that does to the protocol itself.
DeepSeek's V3 follow-up and what 30¢-per-million-tokens means
DeepSeek dropped a V3 update with sharper benchmarks and a price floor that makes the rest of the workhorse-tier market look expensive. The cost per million is interesting; the trajectory is the actual story.
GPT-4.1: the model Microsoft Copilot really runs on
GPT-4.1 quietly shipped this week and it's the most interesting OpenAI release of the year. Not because it's the most capable model, because it's the model the business actually runs on.
Your style is your IP: what AI ownership should actually look like
The legal frameworks around AI training data are still arguing about the wrong layer. The interesting ownership question isn't whether your text was scraped. It's whether the captured shape of how you reason is yours.
Llama 4 lands: open weights at frontier scale
Llama 4 is the first time Meta has shipped a mixture-of-experts open-weights model at frontier scale. The release is more interesting for what it implies about Meta's strategy than for its benchmark wins.
AWS Bedrock through a small-shop lens
Bedrock is built for the enterprise integration story. Most of the AWS-doc treatment assumes that audience. Worth working through what the small-shop or solo-developer version of using it actually looks like.
Treating an AI like an employee: what actually changes
The framing has become a cliché. The actual mechanics, onboarding, scope of work, performance review, termination, change in interesting ways once you take the metaphor literally.