GuideAI in production
Model inference: what happens when you ask AI a question?
What a model does when you ask a question, how we got here, and how to choose between local and hosted inference without confusing fast text with useful work.
Articles
Guides, news and explanations about AI and reliable systems.
ExplainerAI in production
KoboldCpp 1.123 makes agent approvals depend on the tool and workdir
The global auto mode is only part of the permission decision. Follow per-tool overrides, directory scope and restored settings through a copied-runbook exercise.
ExplainerAI in production
Anthropic Scion puts source control behind a cache hierarchy
Scion reduces repeated repository work for online agents. Its cache hierarchy explains why warm checkout speed and fleet recovery need different tests.
GuideAI in production
What is OpenShell and how do I use it?
Run an AI agent with useful access to files and services, then test exactly where OpenShell stops it. A hands-on guide to sandboxes, policy, credentials, and SRE workflows.
ExplainerAI in production
AMD Helion separates agent execution from model inference
Helion places CPU agent loops, token routing, GPU inference and supporting services in separate capacity zones that still share one task outcome.
ExplainerAI in production
Scheduled AI work needs an execution contract
Bind the schedule to a model, tools, input state, destination and acceptance evidence, then reconcile the actual run before retrying or declaring success.
ExplainerAI in production
Bit-exact decoding turns inference speedups into testable changes
Compare reference and speculative paths for token-level equivalence, then run a separate capacity trial so speed cannot conceal a serving-contract change.
GuideAI in production
Build an inference compatibility suite before changing the runtime
Pin the model artifact, template, runtime and hardware, then exercise fixed protocol tests and preserve raw differences before approving a serving change.
ExplainerAI in production
Coding agent benchmarks: what actually won?
A coding agent's tools and testing policy help determine its benchmark result. Understand what was compared before choosing a setup for your team.
GuideAI in production
Auditing AI-generated tests and documentation before cleanup
Review the claim each test or document protects, challenge the evidence, and record a keep, rewrite or retire decision before deleting repository history.
ExplainerAI in production
Running Codex CLI as a supervised worker process
A host that launches codex exec must own the process, thread lease, JSONL trace, cancellation and artifact checks. Resume is a lifecycle decision, not a shell shortcut.
ExplainerPlatform engineering
What Basalt changes in a Blackwell local inference stack
Basalt narrows local inference to Qwen3.8-Flash-Next on Blackwell. Its memory and concurrency controls matter more than copying the largest throughput number.