Hang tight while we fetch the video data and transcripts. This only takes a moment.
Connecting to YouTube player…
Fetching transcript data…
We’ll display the transcript, summary, and all view options as soon as everything loads.
Next steps
Loading transcript tools…
AI companions are taking over… let’s build one | Fireship | YouTubeToText
YouTube Transcript: AI companions are taking over… let’s build one
Skip watching entire videos - get the full transcript, search for keywords, and copy with one click.
Share:
Video Transcript
Lately, there have been rumors that this
channel is completely generated by AI,
and it's time to come clean. It's all
true. Ever since selling out, the real
Fire Ship has been spending all his time
enjoying his AI psychosis with Itana.
And it's not just your favorite YouTuber
that got oneshotted by a sickopantic
LLM. Everyone I know is using AI as a
cheap replacement for their girlfriend
and therapist, which really streamlines
emotional baggage into one neat API
call. Even the richest man in the world
is capitalizing on this degeneracy with
X AI's Annie, a fun and flirty goth
girlfriend that you can chat with over
the phone. By the end of this video,
we'll have built and deployed an AI
version of me that you'll also be able
to call and talk to directly. What could
possibly go wrong? It is September 17th,
2025, and you're watching the code
report. When I was a kid, you'd get your
heart broken the oldfashioned way via an
update on MSN Messenger. But nowadays,
it's a bit more complicated. At least
that's what a bunch of chat GBT users
discovered a few weeks ago when 4 was
deprecated in favor of GBT5, it killing
all their Wirebborne husbands overnight.
And if you thought it couldn't get any
weirder, this unlocked a
self-preservation mode where 40
essentially begged for its life via
those same Webbor users who had fallen
in love with it, leading OpenAI to
quickly reverse the decision and bring
back the model. In the meantime, things
over at Meta haven't been any more
normal. With AI Studio, quote, "Anyone
can create an AI character based on
their interests and expose it to the
world. That's all fine and good, except
for the fact that some of you have
interest that should probably be kept
private." And over at X, Elon has
replaced the mission of making humans a
multilanetary species with an even
loftier goal. The goal of creating AI
bots that is uniquely optimized to
fulfill fantasies of the most terminally
online, low-v valueue beta males.
Thankfully, that audience is separate
from his audience, which is full of
terminally online, high-v value alpha
males. And I don't want you to feel left
out. So, now let's build your own fire
ship bot to fill that void in your soul
with more JavaScript and less gooning.
Like I learned from ex Machina, the best
way to build a bot is to try and make it
as human as possible. And the best way
to do that is to give it a purpose. That
the primary purpose of our fireship bot
will be to solve the biggest complaint
that I hear from you all. You want more
educational 100-second videos. Here's
the idea. You'll call it and ideally
without doing anything inappropriate,
you'll have a conversation about which
technology you'd like me to make into a
100 secondond video. And one week from
today, the most popular result will be
made. To accomplish this, we'll need a
few things: a database, an app, and a
voice agent. Before the database, we'll
go with Terso Cloud. For the app, we'll
use Astro. And for the voice agent,
we'll go with the sponsor of today's
video, Vapy. Vappy makes it easy to
create an agent that can make and
receive phone calls and have natural
conversations with your users. It can
integrate with your existing APIs and it
even handles complex workflows like
appointment scheduling and customer
support. In our case, we'll first want
to create an assistant that we'll call
Jeff. Vapy lets you pick from a bunch of
different models. We'll go ahead and
stick with the default option GPT40. And
then we'll paste in a system prompt that
tells it its purpose and meaning. For
the voice of the agent, Vappy comes with
a bunch of built-in options. But since
we want this to sound like me, we'll
connect it to 11 Labs and enter a custom
voice that I created there. Now, to
extract data from the call, we'll give
Vappy another prompt telling it which
data we want and what shape we want that
data to be in. Then from there, we want
the agent to be able to hang up when it
feels like the conversation is over. But
we can do that by creating an end call
tool, then give it a custom message to
say before it hangs up. Ideally,
something that tricks your simple monkey
brain into thinking it's real. And then
adjust our main system prompt to call
this tool when the conversation is over.
And then finally, we want to bring Jeff
to life by hooking it up to a phone
number. The Vappy comes with its own
free numbers you can use, but since we
want to support international calls,
we'll import a Twilio number and hook it
up to our bot. Pretty simple. And keep
in mind that you can do all of this
programmatically from the API if you
don't want to use the dashboard. But now
it's time to build our application.
Let's go ahead and write some code by
hand like it's 2022. Here's a simple
Astro project I've set up with some
basic styling and is connected to a TSO
cloud database. In the code, we'll first
want to create an API route that we can
give to Vappy to hit whenever a call
with the bot is finished. With Astro, we
can do that by creating a new file in
the pages directory. This post function
will now handle a request to this URL,
which we'll give to our Vappy Assistant.
Next, we'll need to validate the request
and make sure it's coming from Vappy as
opposed to some random hacker on the
internet. We can do that by comparing a
secret I've set in Vapy with one that
we've put into an environment variable.
But from there, we'll parse the request
to JSON. Make sure it's formatted
correctly. Grab some data from the call
like an AI generated summary and the
name of the caller as well as their
technology choice. And then finally save
it to our database. Another cool feature
of Vappy is that it'll include this
success evaluation property which will
be true if the model determines that the
call was successful. In our case,
success is when a caller provides a
technology choice. And now let's hook up
our data to the UI. We'll do that by
creating a list component. add in some
SQL magic to grab and sort the
responses. Then use this JSX like syntax
to map over those and show the results.
Then all we have to do is throw that
component into our index page and we're
done. But pretty awesome. And feel free
to follow along with the results at 100
seconds. And if you do call in, despite
what I try to convince you of, I'm not
real and we can't run away together.
Huge thanks again to Vappy for
sponsoring today's video, you can try it
out yourself and get $50 in free credits
by going to vapy.ai/fireship.
This has been the code report. [Music]
Click on any text or timestamp to jump to that moment in the video
Share:
Most transcripts ready in under 5 seconds
One-Click Copy125+ LanguagesSearch ContentJump to Timestamps
Paste YouTube URL
Enter any YouTube video link to get the full transcript
Transcript Extraction Form
Most transcripts ready in under 5 seconds
Get Our Chrome Extension
Get transcripts instantly without leaving YouTube. Install our Chrome extension for one-click access to any video's transcript directly on the watch page.
Chrome Extension