Practice · 2023–now · AI Present
Local inference
Run the model on your laptop or rack. Privacy, cost control, and the refusal to send every token to a vendor.
Local inference stuck for privacy-sensitive and offline workflows as open weights and IDE-local models matured. It failed as a default for teams that needed frontier quality without GPU ops. The fad was "replace the API tomorrow"; the stuck practice is hybrid — local for routine, cloud for peak.
Case studies
Context
Demos consolidate; evals remain
AI pair programming changed how code is typed faster than how it is reviewed. Agent frameworks and standalone vector stores sorted into demos versus durable plumbing; mid-market RAG folded back into Postgres. The permanent layer is familiar: evals that gate deploys, model routing for cost, tool protocols instead of plugin snowflakes, and humans who own production. Autopilot rewrites and vibe-shipped auth middleware are still big-bang migrations with better slides — and a longer on-call.
Compare with
Related
Framework · 2023–now
LLM app frameworks
LangChain-class glue gave way to vendor SDKs and thin wrappers. The durable pieces are boring: evals, retrieval, and product UX.
Platform · 2022–now
Vector DB gold rush
Specialized embedding stores sold as the default. Mid-market folded back into Postgres — after the vendor tour.
Practice · 2021–now
AI pair programming
Autocomplete that understands the file — now table stakes. Generation outran review capacity; ownership is the bottleneck.