[jldugger]

I think the request here is not about sounding like Majel Barrett but in keeping the output extremely terse and unobtrusive.

There's been a few studys showing that novices love LLM output that's long, but experts hate it. As an example, I've been tasked with using some agentic PM tool to write specs, and it keeps generating these huge page long outputs with "HBR voice" bolded summaries of paragraph long bulletpoints. I.e.:

> Right-size hard, and watch the one open-ended edge. Endorse the DRI's simplifications wholesale: drop the runbook-per-alert mandate (keep 1–2 diagnostic-only runbooks for the high-priority set), and ride durability on the existing weekly incident + monthly operational reviews — no new governance. The single scope-creep risk is the coverage strand (gaps are defined by absence); bound it to gaps evidenced by real, already-missed customer-facing outages, not a proactive gap hunt. Curing ownership gaps (e.g. foo-bar, no clear owner) is finite in-scope work.

There's dozens of these every iteration. I can't imagine trying to deal with that via voice, I would just zone out after the second sentence.

[ijidak]

When the voice models start rambling, I think of C-3PO. When Uncle Owen told 3PO to shut up and 3PO said, "Shutting up, sir."

Or even some scenes where Data did something similar.

It's funny to now experience it.

[elzbardico]

AHAHAHA. HBR Voice. Thanks man, you captured it perfectly. Finally I have a name for that.