Tag: ai
All the articles with the tag "ai".
-
The token tax of Norwegian Bokmål in LLMs
Published:• 2 min readThe same government foreword used 37.4% to 67.5% more tokens in Norwegian Bokmål than in English, despite fewer characters.
-
The one-shot app fantasy
Published:• 1 min readAI helps a capable builder move faster. It does not remove the judgment, QA, customer feedback, and maintenance behind a real product.
-
Designing workspaces for AI agents
Published:• 2 min readChat works for commands. Longer agent tasks also need persistent state, task-specific views, audit history, and rollback.
-
AI agents are useful for old software backlogs
Published:• 2 min readAgents can inspect stale bugs, duplicate issues, old PRs, and half-finished ideas without getting bored. The decision still needs evidence.
-
From AI assistants to agentic delivery workflows
Published:• 2 min readFor DocEngine, I want a shared issue-to-PR process with repository instructions, automated checks, and explicit human approval.
-
A safe pattern for AI-assisted migrations
Published:• 2 min readI use AI for uncertain classification, deterministic code for final writes, and human review when a mistake is hard to reverse.
-
What comes after the AI-generated demo
Published:• 1 min readAI can produce a convincing first version quickly. Product work starts with real integrations, edge cases, tests, operations, and ownership.
-
Fixing OpenClaw with OpenClaw
Published:• 2 min readOpenClaw helped investigate and fix its own bug. The agent shortened the path to a reviewed patch, while humans kept control.
-
Reliable AI agents need operational proof
Published:• 2 min readAn agent should prove what it completed, report failures, and record the lesson so the same mistake does not return next week.
-
From Grok to Obsidian: owning my AI memory
Published:• 1 min readX exported my tweets and media, but not 1,174 Grok conversations. I built a workflow to keep that history in local Markdown.