Getting the transcript
Reading the captions from YouTube. A video nobody has opened here before takes 10 to 30 seconds; this page fills in on its own.
The Wildest Jev AI Use Cases (Including My Ad Account) transcript
Mr. Paid Social · @MrPaidSocial
Published September 21, 20261:5427.7K views
Transcript analysisComputed from the caption text
Words
393
Runtime
1:54
Speaking pace
207wpm
Reading time
2min
207 words per minute, above the 201 75th percentile of 349 measured videos. That distribution comes from the 349-video hook study.
Opening (first 30 seconds)
Here we go again. Brand new AI model just launched that claims to be up to 200 times faster and 400 times cheaper every other LLM. It's because it's not an LLM. Dumb it down as much as I possibly can, think of it as an AI filter. This is how this is fundamentally different. So, you put in is this invoice fraud? The LLM writes it one line at a time and it's really slow and expensive. Give that same prompt to Jev and it runs it through boarding criteria, gives it a score, and it takes 0.1 seconds. A fraction of the
104 words, the words spoken in the first 30 seconds at 207 words per minute.
Free, no signup. See how the first 30 seconds hold attention, with rewrites.
Sentence shape
| Measure | This transcript |
|---|---|
| Sentences | 28 |
| Average words per sentence | 14.0 |
| Longest sentence | 28 words |
| Questions asked | 1 |
| Sentences containing a number | 6 |
Most used terms
- jev7
- ad4
- llm4
- running4
- account3
- ad account3
- ai3
- claude3
- cost3
- guy3
- ads2
- buying2
Filler phrases
1 in total: like 1.
A literal whole-word count of the same phrase list the Prepublish browser extension uses, so a phrase inside another word is not counted and a phrase used in its ordinary sense still is. It is a count and not a judgement.
Check your own script before you film
Free, no account. See where attention is likely to drop, with a rewrite for each weak line. The free check shows the scores and the one issue costing the most. Or run it on the words above first.
Free · No login · See a sample audit first if you prefer.
What this transcript is
Every word below is the caption track YouTube publishes for this video, pulled from the video itself and reproduced unchanged. It is not Prepublish's writing, not a summary, and not a re-transcription: it is the video's own published captions. English captions, generated automatically by YouTube, in the video’s original language. Source: the video on YouTube. A channel that would rather this page did not exist can ask for its removal through the contact page, and it is removed.
No Script X-ray for this video: YouTube shows a Most replayed graph only once a video has enough views.
Transcript
Here we go again. Brand new AI model just launched that claims to be up to 200 times faster and 400 times cheaper every other LLM. It's because it's not an LLM. Dumb it down as much as I possibly can, think of it as an AI filter. This is how this is fundamentally different. So, you put in is this invoice fraud? The LLM writes it one line at a time and it's really slow and expensive. Give that same prompt to Jev and it runs it through boarding criteria, gives it a score, and it takes 0.1 seconds.
A fraction of the cost. That people are building with it already are absolutely blowing my mind. Right here you can see it scrolling ads, running it through 30 unique buying personas, and in real time it's deciding which ones are most likely to buy. And just look at how cheap this is and how fast it's running. This example it's running through 724 live ads across 37 brands and analyzing every single hook, offer, and angle that they're running.
To have an LLM do this would take forever and cost a fortune. This guy made a real-time slop filter for his Twitter feed that would automatically label and hide things as slop. This guy's using it to play a video game. People are using it to make decisions about buying and selling stock. This guy used it to help him find flights. Took 7 seconds and cost 0.0039 cents. Here's Jev versus Claude at doing an SEO audit. Pretty much anything that has a yes no answer, you should be funneling through Jev.
I had Claude code train Jev on my entire ad account history. So, Claude can see exactly how I made every single decision in my ad account for the last 2 years. And then fed that criteria into Jev and now Jev can assign a scale score to every ad set in my ad account. This is just one of like a million ideas I have. You want the link to try this new tool out for yourself, just comment Jev and I'll send it straight to you.
Anything out of this, make sure you give me a follow. I got a lot of content showing you how you can level up everything you're doing right now with AI.
The words are the caption track's own and nothing is reworded or re-transcribed. Paragraph breaks are placed between sentences so the text reads as prose.
Working on a video like this one?
Free tools for your own script: paste a draft and see where it stands before you record it.
Script Audit
Paste your draft and see where viewers are likely to drop off, with a rewrite for each weak line.
Hook Analyzer
Paste the first 30 seconds of your own draft for a hook score and rewrites.
Policy Pre-Flight
Check your draft against YouTube's advertiser-friendly guidelines before you record it.
Channel Skill Generator
Read this channel's public videos and transcripts, and download a writing brief for it.