Pinned Tweet
I built my own harness for video editing and motion design
It writes the story, storyboards it, animates it, and drops everything straight into a timeline in your favorite editor
It can call Blender for 3D, Seedance if you need Al shot, or ElevenLabs for voice though I used none of that for this one because I wanted it to feel hand-made
Can't wait to push it further
First result that I'm pretty happy with :
Luzz retweeted
give a man a fish and you feed him for a day
teach a man to Claude Code and you financially ruin him with distracting side projects for the rest of his life
Luzz retweeted
I built my own harness for video editing and motion design
It writes the story, storyboards it, animates it, and drops everything straight into a timeline in your favorite editor
It can call Blender for 3D, Seedance if you need Al shot, or ElevenLabs for voice though I used none of that for this one because I wanted it to feel hand-made
Can't wait to push it further
First result that I'm pretty happy with :
Luzz retweeted
Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5:
hackertube.org/
- Excellent recs without any logins (state is kept in local browser session)
- Thumbnail is a representative frame from middle of the video instead of the super duper A/B test hyper-optimized user uploads
- Underlying data from the comment analysis as one zip file, point your Claude at it and ask for your own version
- HackerTube Longs ✊
A bit more on the process:
I use Claude Code (desktop app for Mac), Opus 5.5 on Medium effort as my default. I only talk to Claude and have it do everything, the only "manual work" I helped with in tandem was in the browser (reminiscent of MenuGen): 1) I had to create some kind of API key from Google Cloud UI to query YouTube for video metadata, 2) I booted up a VPS box for serving and 3) I bought the domain name. Once the box was up I gave Claude the IP and told it update, secure, harden, deploy and optimize the code, and it did the whole thing.
Many awesome projects that would have normally taken weeks/months even can now be few-shotted for breakfast. What else are we not thinking of.
Luzz retweeted
Today, we're shipping real-time graphics.
Using Sol 6.1 Ultrafast we can generate custom overlays, diagrams, and even interactive 3D scenes right on a user's screen, no chat.
It's a new visual interface for AI.
Here's me learning about LLMs + hardware.
Demo:
Getting smarter and learning more > letting AI do the thinking for you
a really nice example of how to use AI.
this guy has a unique energy and good vibe that’s hard to put into words
some people just give off a solid aura like that, and he’s definitely one of them
Today, we're shipping real-time graphics.
Using Sol 6.1 Ultrafast we can generate custom overlays, diagrams, and even interactive 3D scenes right on a user's screen, no chat.
It's a new visual interface for AI.
Here's me learning about LLMs + hardware.
Demo:
3
99
Claude Code is a piece of shit. gist.github.com/flamerix-ai/…
Luzz retweeted
clucky is probably one of the most beautiful product failures ive seen recently.
doesnt mean it’s dead they can still fix it. but only if they actually face why it flopped.
the design is incredible. memorable brand, cute chicken mascot, original animations... it basically stole duolingo's playbook in the best way possible. even i wanted to download it just because the object looked cool
and that’s exactly where the trap was.
for weeks, their entire build-in-public strategy was just showing off UI.
every screen racked up likes. designers were sharing it, builders were following along.
it’s so easy to mistake that kind of noise for product validation.
except the people liking pretty mockups on twitter are not the same people who desperately need an aggressive alarm to get out of bed. and they're definitely not going to pay for one every morning.
they validated the aesthetic with designers. they never validated the pain point with actual users.
the market is definitely there though. alarmy has been printing millions of downloads for years with math problems, photo missions, and physical challenges.
so the category isn't bad. it's just super specific.
this stuff only works for heavy sleepers, students who sleep through lectures, or people with serious sleep inertia who need an external force to pull them out of bed.
for them, solving a math problem is a fix. for anyone else, it's just a torture device at 7am.
that’s the difference between useful friction and artificial friction. you have to understand what pain people are willing to tolerate to solve a bigger one.
clucky sold a mechanism before understanding the problem.
it started as "an alarm that forces you to do missions" instead of asking who desperately needs this and why.
and then came the killer.
users started leaving reviews saying the alarm simply didn’t go off. one person missed school because of it.
if your core feature fails, literally nothing else matters. a bug in a social app is annoying. a bug in an alarm app destroys the core promise of the product.
design gets you the first download. rock-solid reliability earns trust. and without trust, no one is letting your app handle their wake-up call, no matter how cute the mascot is.
then they slapped a pro subscription on it right away. asking people to pay to replace a built-in phone feature before you've even earned their trust just adds more friction.
what they needed at launch was hyper-narrow positioning.
not "a fun alarm clock for everyone."
it should've been "the alarm for students who are always late to class" or "the alarm for people with adhd who literally can't get out of bed."
then you just watch that specific cohort for a month.
do they actually wake up? which missions work without making them rage-delete the app? do they still use it after 30 mornings?
that's what you monetize.
clucky isn't proof that branding doesn’t matter. the branding got them more attention than 99% of apps ever see.
but hype can't fix bad segmentation. likes aren't retention. and admiring a product on twitter is completely different from actually needing it in your life.
It would have taken me 2 months to do that myself, just getting back up to speed with After Effects and even then, I’m not sure I would’ve gotten this quality.
AI changes everything, the quality and quantity we can ship. small teams are pushing out 200 ads a week.
A lot of people still don’t realize it or aren't leveraging it yet, stuck in the old world.
I built my own harness for video editing and motion design
It writes the story, storyboards it, animates it, and drops everything straight into a timeline in your favorite editor
It can call Blender for 3D, Seedance if you need Al shot, or ElevenLabs for voice though I used none of that for this one because I wanted it to feel hand-made
Can't wait to push it further
First result that I'm pretty happy with :
6
186
Obsessing over distribution without fixing conversion and retention is like bragging about getting 500 Tinder matches when you’ve never survived a first date
1
2
199
If your Head of Growth hasn’t had at least 3 Meta ad accounts permanently banned before breakfast while trying to scale a posture corrector to the moon, don’t trust them with your budget
everyone in tech suddenly wants to hire a growth killer
but you're looking in the wrong places
the best growth people i know didn't start their careers at Meta, Google or some fancy SF startup
here's what we were doing 10 years ago:
> black hat SEO
> dropshipping in bali
> info products & vsl funnels
> affiliate marketing networks
> farming niche YouTube channels
> automating social media accounts
> selling virtual currencies in video games
> building & flipping instagram theme pages
> industrializing NFT collection launches during NFT summer
we were gaming algorithms, exploiting distribution loopholes and figuring out how to make money online
we mastered the art of capturing attention, arbitraging traffic and redirecting it wherever money could be made
we didn't learn distribution from a playbook
we learned it by putting our own money on the line
and here's the funny part
most of the killers i know today still have side hustles making as much money, if not more, than their startup salaries
we're not in tech because we need a paycheck
we're here because making money on the internet eventually gets boring
we want bigger games to play, harder problems to solve and more exciting things to build
we're not corporate marketers
we're internet grinders who got bored and moved to bigger playgrounds
that's your talent pool
2
115
Luzz retweeted
je viens d'être la cible du phishing le + sophistiqué de l'histoire informatique
- je reçois par email une prétendue alerte qui m'indique que j'aurais généré un accès tiers à mon compte Google pour un utilisateur @gmail que je ne connais pas
- l'email de l'émetteur no-reply@accounts•google•com a tout d'un mail officiel @Google et Gmail ne mentionne pas la moindre alerte de suspicion
- je clique sur le lien, car le site de phishing hébergé sur le domaine google•com semble 100% legit, il fait même semblant de faire des vérifs de sécurité avec un CAPTCHA
- même mon password manager me propose de remplir l'email/pwd car j'ai un vrai compte sur sites•google•com (c'est Google qui offre l'hébergement de sites web)
- si je remplis les champs email/pwd, le hacker les récupère instantanément pour se loguer et récupérer tous mes accès Google/YouTube
cette attaque va faire mal, j'ai report à Google
comment j'ai compris que c'était du phishing ?
1 : le bouton d'action des emails Google est sensé être le gros bouton bleu, pas un lien juste au dessus
2 : en allant voir dans les détails le sender [mailed-by] est fwd•privateemail•com et non *bounces•google•com
A Growth tactic I used back in 2020 that most people have forgotten
Turning a real press article into a conversion layer without building an advertorial
Here’s the idea
🤖 Made with AI
This is NOT an advertorial.
Advertorial:
you build editorial-looking content yourself.
This:
the article was genuinely published by the media outlet
You’re simply adding a clearly branded conversion layer around it.
1
24









































