Bayram Eker
EN
CV Start a conversation

Home / Writing

Writing: AI

Writing on artificial intelligence, decision-making and the engineering that turns models into useful, understandable systems.

Choose a topic and a format to narrow the archive.

Clear filters
An engineer arranges blank cards and a floor plan beside a sensor module, with a stationary mobile robot and a separate work cell in the background.

Why did you call me?

A robot pauses an inspection and asks for help. What its message tells a busy person matters as much as how convincingly the AI can write.

Read
  1. Program state enters a decision model; a typed result and its uncertainty pass to a policy in code before an action is taken.

    When software needs a decision, not another paragraph

    A billing message needs the right destination. TypeSafe’s Jev offers one way to turn an interpretation into a result that software can act on.

  2. A model proposes an action, the harness checks authority, and the environment returns evidence for the next step.

    When an AI agent says “done”, what should we check?

    A convincing completion message is only the beginning. Harness engineering is the work of helping an agent act, check the result and recover when needed.

  3. Three small warehouse robots wait beside shelving where a pallet blocks a narrow passage.

    When a hundred robots share one passage

    A pallet left in an aisle can hold up a whole fleet. From that small interruption, a story about robot teams, communication and the possible role of quantum computing.

  4. Hybrid quantum and classical systems in a defence context

    Four questions I am taking into 2027

    My expectations for hybrid AI and quantum systems, written in August 2026 with a few clear signs that could make me change my mind.

Also available as an RSS feed.

Keep exploring

Another way into the work.