Using @typesafeai's Jev, each time judging Local Whisper's
Automated MacBook control by running Local Whisper transcripts through Jev to decide each action, driving Chrome and Slack via accessibility APIs.
The original post, translated
Using @typesafeai's Jev, each time judging Local Whisper's text generation, automating operations on the Macbook's local computer, I tried doing all sorts of things!
Chrome pages are recognized and operated via Browser Harness, Slack and Notion are recognized and operated via Mac's Accessibility.
Implementation is limited to Grok 4.6 (because of Codex's limitations)
Show the original post in its source language ▾
. @typesafeai のJevを使って、Local Whisperの文字起こしを都度判定して、Macbookのローカルコンピュータの操作を自動化して、あれこれするのやってみました！
Chrome のページは Browser Harness、Slack やNotionは Mac の Accessibility で認識して操作してる。
実装はGrok4.6のみ(Codexの制限きてたんで）
The post above is a machine translation from ja; the untranslated text is in the fold-out.
Quoted post
@kzkhykw1.2K viewssourceHello World
Engagement when collected
Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.
Where this case fits
Filed under coding & developer tools, browser & computer use. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the coding & developer tools page.
Related Jev cases
Breaking: Browser Use + Jev = Ultrafast Findings flights
AgentsBrowser agents
The gains aren’t free: Jev can't generate text Comparing
Dev toolsClassification
Jev VS Fable 5.1 VS GPT-6 Astra: chess typesafe's new Jev
GamesDev tools
The open-source local version Laya's response speed crushes
Dev tools
Keep browsing: all 1173 Jev cases · more from @kzkhykw · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post