Local Whisper hears everything; Jev decides which action to take, in real time.
Marc Köhlbrugge is building a computer assistant with Jev. A local Whisper model listens to everything he says, and Jev classifies it to decide which action to take. A small Swift app gives Jev the full accessibility tree, so it knows what is on screen and what can be clicked. He calls it early but promising, and it all runs in real time.
Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type (this video is at 1x speed btw) Built a tiny open source browser agent. try it below ↓
@gregpr07 · Agents & browsers · ~$0.004 · ~7 s
@gregpr07
X post
Agents & browsers
~$0.004
~7 s
# Jev: AI Decisions as a Typed Function Call What I learned using TypeSafe's Jev for code review, and why its more surprising uses are browser control and generative UI.…
stacktoheap.com · Agents & browsers
stacktoheap.com
Resource
Agents & browsers
-
-
Chrome extension that labels every post you scroll past on X with six typed questions per post, and counts what it costs in the corner.
oso95 · Agents & browsers
oso95
GitHub
Agents & browsers
-
-
Chrome extension that scores draft posts and reply context before posting; optional media descriptions come from a separate vision model.
RafalWilinski · Agents & browsers
RafalWilinski
GitHub
Agents & browsers
-
-
building a computer assistant with Jev local whisper listens to everything I say which then gets classified by Jev to determine what actions to take it uses a small Swift app to provide the full accessibility tree to Jev (i.e. tell its what's on my screen, what can be clicked, Show more
