ACAI CHRONICLE.
Subscribe

ENTITY ARCHIVE

METR

Articles mentioning METR. A growing collection across our topics.

7 stories

Two coding workflows compared against the same abstract code task and review markers.
AI at work / Comparison

Cursor vs. GitHub Copilot

A standalone editor against a plug-in assistant, compared feature by feature.

AI code changes entering a workspace and being traced by a human reviewer.
AI at work / Review

Cursor review: coding workflow and review effort

How Cursor's features fit together, and the review work left.

Inline coding suggestions passing through accept, reject and test gates.
AI at work / Review

GitHub Copilot review: coding tasks and limitations

Copilot's plans, agents and limits after the move to credits.

A coding task expanding into file changes, tests and a reviewed result.
AI at work / Review

Claude Code review: from task to reviewed change

One coding task followed from brief to merge in Claude Code.

Terminal and editor coding workflows compared on the same repository task.
AI at work / Comparison

Claude Code vs. Cursor: choosing a coding workflow

Terminal agent or agent-first editor: where review happens and what it costs.

A visible productivity gain above hidden review, correction and failure work.
AI at work / Analysis

How to measure AI productivity without hiding review work

Count the checking and fixing, not just the draft time saved.

Different workplace studies arranged by tasks, populations and outcomes.
AI at work / Analysis

What workplace AI studies actually show

What the best workplace studies measured, and how far it travels.