Tag: ai
All the articles with the tag "ai".
-
AI agents need queues, not infinite loops
Published:• 6 min readAfter letting Codex run a goal for more than 14 hours, the lesson was not that agents should run forever. The useful pattern is a queue of scoped tasks, clear evidence, and human ownership at the right points.
-
The review bottleneck is the new software bottleneck
Published:• 12 min readAI agents can generate code faster than teams can understand it. The bottleneck in software development is shifting from writing code to reviewing, verifying, and owning it.
-
When the best AI security reviewer refuses to review security
Published:• 4 min readI tried using Claude Fable 5 for a defensive security review of our SaaS application. Even with safe framing, it refused and fell back to Opus 4.8.
-
AI-assisted 3D printing: from idea to object with my son
Published:• 3 min readA small weekend maker project with my son: using an AI agent, parametric CAD, and a 3D printer to turn a hanging solar bulb into a desk light stand.
-
Taking ownership of your AI coding history
Published:• 3 min readAI coding assistant history is becoming valuable development memory. Developers should be able to export it, inspect it, archive it, and reuse it responsibly.
-
Warp as an ACP Client
Published:• 3 min readAn experimental prototype of Warp running as an Agent Client Protocol client, separating the terminal UX from the user-owned agent runtime.
-
The next AI interface may not be a chatbot
Published:• 2 min readChat is useful, but the next layer of AI interfaces may be dynamic workspaces that adapt to the task.
-
The token tax of Norwegian Bokmål in LLMs
Published:• 2 min readA small experiment comparing English and Norwegian Bokmål token counts for the same official government text.
-
The one-shot app fantasy
Published:• 2 min readAI can multiply a capable builder, but serious products still need judgment, architecture, QA, customer feedback, and maintenance.
-
AI agents need workspaces, not just chat windows
Published:• 2 min readChat is a useful command layer for AI agents, but it is probably not the final interface. Real work needs state, structure, and rollback.