teaching how to code with AI on YouTube (55k) and growing @lumail_io to 10k MRR - 📧 pro@melvynx.com
Bali, Indonesia
- Tweets 38,030
- Following 822
- Followers 25,656
- Likes 28,731
Pinned Tweet
Hey, I never properly introduced myself, so let's start:
I'm Melvyn, 23, and I've built a French developer community of 50K+ subs on YouTube.
Looking to connect with more international people, so I'm switching to English-only posts here!
I build a lot of projects:
→ saveit.now - bookmark tool
→ lumail.io - email newsletter
→ thumbfa.st - YouTube thumbnail generator
Let's connect. Don't hesitate to DM me!
25
1
130
70,293
Why we talk about Fable 5.5 ??
someone built a Waymo teleoperator with San Francisco map.
play here: teleoperator.mindblown.ai
stack: fable 5.5 and threejs
i know its ai, its vibecoded, but i can't get a profitable waymo trip. can you?
2
16
4,260
Melvyn • Builder retweeted
.@JotaroSeo m'a fais exploser Trendtrack en SEO
A +1M mrr j'ai envie faire un podcast avec les équipes comment on a enculer le marché on pourra en parler un peu dedans
C'est dans une logique que je recommande son SaaS pour avoir vu ça, il gère egalement le SEO de Digifeel
C'est pas les autres tools de con que j'ai testé la je sais y'a des résulats et un mec avec du niveau lol
5
7
59
11,887
Bridge Mind shit account let’s support Theo
I apologize in advance for this crash out, but holy shit I'm so tired. I'm trying to figure out what is even being measured here and it's nearly impossible.
I read the post. It provided no insight whatsoever into how these "tests" work.
Things that were not mentioned:
- Harnesses used
- Tasks used
- How many times tasks are run
- What is done to identify variance in daily runs
- What analysis is done on "bad" runs to detect root causes for failures
- What APIs are being used (matters a LOT)
- How the +/- 10% "variance" was selected
- Why tokens and costs are "weighted" the same, and combined rank roughly as high as intelligence
- Why tokens are included at all when costs are the metric that matters
I'm sorry @bridgemindai - am I missing something here? I just want to make sure I understand fully before building my own alternative bench.
I DM'd you asking for traces from your runs, would be super helpful as I start digging deeper here.
2
6
1,609
Melvyn • Builder retweeted
Introducing image-viewer!
A simple Claude Code mod that renders the images you paste above the prompt input.
github.com/jarrodwatts/claud…
44
57
1,062
55,591
Melvyn • Builder retweeted
Nouvel épisode pour @LePodcastIA.
On apprends que @melvynx est polygame tandis que je prépare un tatouage à l'effigie de notre futur sponsor.
On aborde aussi d'autres sujets plus sérieux :
- Fin des abos IA cheaté à 200$
- La fin des monteurs vidéos (et la suite)
- Le basculement d'ère qu'on est entrain de vivre
Et la question centrale de cet épisode...
Est-ce que toi aussi t'as des orgasm** avec Claude ?
Allez... bon épisode. 😉
2
4
9
708
For French speakers 🇫🇷, I just published my HARD CORE podcast with @YannisHaismann and @JohnLrDev where we talk about:
• why developers have orgasms with Claude and Codex
• why video editing is dead
• open 500 subs, soon 1000 and then 10k subs?
Link here: mlv.sh/lepodcastia-2?e=3
3
4
15
1,226
Melvyn • Builder retweeted
Cloudflare's new decision model can see 👀
clef-flash running locally on my M5 Max
weights are Apache 2.0. go wild!
the Cog work from Replicate is now part of how you fine-tune and redeploy models on Workers AI 🔥
first up is Clef: open weights, Jev API compatible, and clef-flash runs ~13x faster than Jev
43
94
1,527
123,187
this is so smart wow
You can now mod Claude Code:
- Change how it behaves
- Customize the UI
- Swap in your own features
Write one with a few lines of TypeScript, or have Claude build it for you. Mods ship inside plugins, so you install them with /plugin in the CLI or desktop app.
A few examples:
7
1
40
8,723
Melvyn • Builder retweeted
The interview with @thsottiaux from OpenAI 🔥
0:00 Everything OpenAI launched at DevDay
2:44 Sponsors: Wispr Flow, Hostinger, OpenArt
4:11 What is ChatGPT Dots?
7:52 Will ChatGPT Dots be free?
10:15 GPT-6.1 Sol vs GPT-6 Astra
11:44 Is AI now building AI?
12:53 Ultra Fast: when does everyone get it?
14:00 How OpenAI rebuilt the ChatGPT desktop app in 30 days
19:08 Why everything will run in the cloud
20:55 Calling your Dots on the phone
22:11 The new Turing test
24:05 OpenAI's mission and AI safety
26:14 Why OpenAI still works like a startup
27:29 The truth about ChatGPT usage resets
29:00 The $500 ChatGPT plan
30:17 Sponsors in action
32:23 Why AI agents still fail
33:52 OpenAI's AI is now on call
34:26 OpenAI's internal benchmarks
35:55 Open source Codex and the open ecosystem
38:42 ChatGPT Space explained
39:45 Is the chat box holding AI back?
42:26 Every DevDay update, full workshop
43:28 How people really use ChatGPT Work and Codex
44:01 When is the next OpenAI model coming?
45:05 What AI has to solve next
45:32 Is your job safe from AI?
48:14 Rapid fire
48:54 Has OpenAI already reached AGI?
50:48 The one thing he'll never let AI do
51:22 His morning AI routine
52:15 What he'd build if not AI
Watch the full podcast on YouTube or X.
Enjoy!
70
61
545
235,344
« Mais quelle ingéniosité ! »
Le @Chef_Etchebest n’en revient pas : ce restaurateur récupère des portes de frigo pour en faire des plans de travail ! 😅
#CauchemarEnCuisine – épisode inédit, mercredi 30 septembre à 21:10 sur M6 et en streaming sur @M6plusofficiel
45
87
2,033
1,317,264
Melvyn • Builder retweeted
I'm pleased to announce [REDACTED], a suite of free tools that redact sensitive data without your files ever leaving your device!
→ Face & video blur
→ PDF redactor
→ Chat anonymizer
→ and more
100% free, runs in your browser
link: redacted.to
70
10
322
20,160
Melvyn • Builder retweeted
Claude Opus 5.5 wrote the piano music in Python, created the 3D animation in Python, and rendered it in Blender.
90
176
2,793
185,845
years later, google wake up
We're introducing skills in @GeminiApp to help you automate your most repetitive tasks.
Now, you can now save your most-used instructions once and run them endlessly by typing a '/' in the prompt bar.
5
23
3,056
bro doesn't respect anyone anymore, let's react
The fact that instead of adapting to industry , one of the biggest channels in coding before AI decides just to attack other creators is funny
I didn’t watch a video and do not really care. I am not the biggest fan of @theo content but this is just beyond normal
2
1,324
