LLM engineering
44 posts
Your decisioning problem isn't accuracy.
Run open-source decision models locally-pinned versions, validation, immutable logs-so every approval or denial stays reproducible and auditable.
Claude optimizes what it measures
Claude only makes faster what you let it measure. Build the measure-change-verify loop, carry guardrail metrics, and verify every change against a baseline.
Cloudflare ships Python Workers to general availability
How to wire Cloudflare Python Workers into automation pipelines as validated, Queue-connected stages for reliable, scalable AI systems.
A 4B model outplans Postgres
A 4B model proposes faster Postgres query plans, but the validation gate and fallback - not the model - are what make the 81% speedup safe to run.
Distillation makes fast followers, never frontier leaders
Distilling frontier models is a real, cheap fast-follow strategy for small labs - but only for verifiable tasks and legally usable teachers.
Google quietly broke the search-scraping stack
Google's 2025 anti-scraping update killed cheap SERP scraping. How to rebuild AI search pipelines on sanctioned APIs, validation, and budget controls.
Turning off training does not protect your data
OpenAI keeps re-enabling 'allow training.' Why a UI toggle is not a data control, and the gateway-and-contract architecture that makes training exposure impossible by design.
SWE-2 is the wrong model for almost everything
SWE-2 is a code-execution node, not a generalist replacement. How to eval it against your own repos and where it actually fits in production pipelines.
The weaker model matters more than the smarter one
DeepSeek v4.1 Flash cuts token cost, not the need for validation - use it in cascades, verification loops, and long-context pipelines that hold up in production.
Context is the whole bill
Portal by Spotify cut Claude Code token usage ~90% by serving scoped code slices instead of whole files, and why that matters for production AI systems.
Same task, different bets
Claude, Codex and Cursor pick different tools across 17k runs - here is how to measure that revealed policy and wrap it in controls before it hits production.
The best terminal assistant has no AI
TERMy runs without an LLM to show where deterministic retrieval beats AI-assisted terminal work: bounded inputs, known answers, instant offline lookups.