Did
Theo
mention me?

We scan every video for X posts on screen, then check the transcript to see if they were read aloud. See everything Theo showed.

Search by

Every post with your handle on screen. A profile or post link works too.

Matches the text of one post, even if the handle was cropped out.

A few words you remember. Matches by words and by meaning.

@ThePrimeagen

Yes.

Theo showed your posts 6 times and read 3 aloud.

Post on X ↗
  1. On screen 18:31Read aloud 13:37
    pstack creator spends $132,000,000/year on ai????
    ThePrimeagen@ThePrimeagen

    After Astra released I once again am waiting for this 10x cheaper AI per year thing I keep being promised...

    Theo read it aloud at 13:37
    And this is where I need to talk about what Zeig said.
  2. On screen 54:52
    I'm getting impatient...
    ThePrimeagen@ThePrimeagen

    Hey, it is Wednesday OpenCode hacked > Happy getting internet getting humped day

    Shown on screen for about 5 seconds. Not read aloud.

  3. On screen 0:59Also on screen at 3:29Read aloud 1:06
    I thought AI was gonna get cheaper?
    ThePrimeagen@ThePrimeagen

    After Astra released I once again am waiting for this 10x cheaper AI per year thing I kept being promisẽd... After Astra rele year thing I kep 9:51 AM · Sep 8, ?

    Theo read it aloud at 1:06
    by Primagen, because he made a tweet referencing a real promise that Sam Altman had made, which is that he said AI would get 10 times cheaper year over year.
  4. On screen 10:21Read aloud 10:21
    finally a good small model
    ThePrimeagen@ThePrimeagen

    tested out Haiku vs Luna reasoning none for some automation Haiku, literal drop in replacement (it was a one line change of changing a string in a config file), performed significantly worse Still have to understand why It was also significantly slower (both in pass and fail) tested out Haiku vs Luna reasoning none for some automation Haiku, literal drop in replacement (it was a one line change of changing a string in a config file), performed significantly worse Still have to understand why It was also significantly slower (both in pass and fail) model, reasoning model, reasoning openai/gpt-6-luna, none anthropic/claude-haiku-5.5, none so it wasn't some trick of which model i was using.

    Theo read it aloud at 10:21
    Bias got notified by my chat that Prime tweeted he was using Haiku in some work he was doing with reasoning off for automations.
  5. On screen 11:39
    I love Ultrafast (it's unusable)
    ThePrimeagen@ThePrimeagen

    I bought the $500 plan today, prompted for ~60 minutes welp.. it was a good 56% of my weekly limits Server: Local background server

    Shown on screen for about 34 seconds. Not read aloud.

Opens in a new tab.