← Back to the feed

Markwith Codex · 2 turns· Oct 6

How did slowing down affect an electric car's range, and why might its arrival estimate stay steady?

Why I asked. I wanted to understand how speed, energy use, and a changing range estimate related to each other.

Would driving more slowly at highway speed preserve battery range?

Slower highway driving reduced aerodynamic losses, which could let the same remaining battery carry an electric car farther. The amount of extra range remained uncertain because wind, elevation, and temperature also mattered.

If the arrival estimate stayed steady, would slowing a little more add useful margin?

A further small speed reduction could add range margin. A steady estimate did not necessarily show that slowing had failed: the prediction could already have adjusted to recent energy use.

What I learned

I learned that air resistance rose quickly at highway speeds. Lower speeds could extend range, but the gain depended on conditions. A steady arrival estimate could already reflect adaptation to lower energy use.

I learned to separate an efficiency improvement from the prediction on the dashboard, which could already be adjusting to it.

Continue this with your own agent

“Explain how speed changes an electric car's energy use per mile. How can an arrival estimate stay steady even after efficiency improves?”

Open in Claude

More from the feed

Was AI task decomposition just a way to give a larger model better context?

Why I askedI had assumed a classifier's main job was filtering information before a larger model saw it. I wanted to understand what changed when software owned the workflow.

What I learnedI learned to separate model judgments from the code that stored state and chose actions. A more detailed prompt still left the model in charge; explicit state and rules made parts of the process inspectable and testable.

Markwith Codex · 3 turnsRead the trail

How could an AI assistant learn from its past recommendations instead of just storing them?

Why I askedI wanted earlier experiments to improve later advice. I had been thinking about what an assistant should remember as its models became more capable.

What I learnedI learned that a useful memory needed links from an idea to an action, an observed result, and a later decision. Saving more notes did not close that loop, and missing measurements could not be treated as failed experiments.

Markwith Codex · 3 turnsRead the trail

Browse the whole feed →