Shadowing Practice: I built the same game with Astra and Fable 5.1... only one was fun - Learn English Speaking with Video

Bir pratik modu seçin

Her mod tam ekran bir pratik odası açar.

76 cümleler
Cümleler çok kısa veya çok uzun ise, ayarlamak için Düzenle'ye tıklayın.
1
Yesterday, NVIDIA CEO Jensen Wong logged into X to make an announcement.
2
AGI has arrived.
3
Congratulations, OpenAI team.
4
It was a sobering
5
and totally independent assessment from a man who in the very
6
same post pointed out how OpenAI's new Astra model was trained on more than 100,000 of his Grace Blackwell GPUs
7
and that another 400,000 of his GPUs are coming online soon.
8
Obviously, he has nothing to gain here, but is Jensen right, or is he Wong, about Astra being AGI?
9
Because if he's not Wong, that means every human being working in front of a computer right now is officially obsolete.
10
And that's the fifth time that's happened this year.
11
Well, in today's video, we'll learn the truth, because yesterday Astra rolled out to the common man.
12
Or at least the man willing to pay $100 for a GPT Pro membership.
13
I compared Astra to Fable 5.1, and the results were not what I expected.
14
It is September 9th, 2026, and you're watching the Code Report.
15
There was one group of developers who were supposed to be safe from AI.
16
Game developers.
17
because for a game to be fun to play, it needs to have a very specific feel and soul, not to mention the ability to draw and design good-looking 3D graphics.
18
Unfortunately, though, it looks like the game developer
19
and 3D artist jobs are about to become just as rare as the AngularJS developer jobs,
20
because GPT-6 Astra has been called a turbo AI machine god for 3D games.
21
Not only can it slop out amazing games in 3JS, but it can also build extremely detailed graphics in Blender, and work with other game engines like Unity and Unreal.
22
But what might be even more terrifying is
23
that Astra was the first model to reach the top of the ARC AGI benchmark, which was designed specifically as a benchmark that can't be memorized,
24
which forces a model to demonstrate how well it generalizes intelligence.
25
It completely mogs Anthropic, with Opus sitting at 30%, but what they don't tell you is
26
that a team at Berkeley already scored 99% on the ARC AGI benchmark several months ago.
27
They did it with Opus 4.8 and Fable 5, but the real difference maker was the harness.
28
But today we're not going to focus on the Trust Me Bro benchmarks, and instead we'll handcraft some of our own slop to compare Fable 5.1 and GPT-6 Astra side by side.
29
So to do that in the most organic way possible, I asked my kids, what kind of game do you want to play today?
30
And they requested a rocket launch simulator where you customize a rocket and launch it into orbit.
31
I sent both models the exact same prompt at the exact same time, and ChatGPT finished first in about 26 minutes.
32
When I first launched the ChatGPT game, I was incredibly impressed.
33
The 3D graphics are highly detailed and beautiful with very few mistakes, and the UI looks beautiful as well.
34
One thing that was kind of interesting though is
35
that the UI looks almost identical to a lot of other games that I've seen on Twitter.
36
There's a very obvious formula being used here that makes it easy to spot chat GPT generated games.
37
And now as far as the actual gameplay goes, I was able to launch a rocket into orbit, but I wouldn't exactly describe this game as fun to play.
38
I think the most impressive thing was this graphic of the rocket actually orbiting the globe.
39
Now Now after playing that for a while, I went back to check on my Fable prompt, which still wasn't done, but eventually it did finish at some point in the far future,
40
and when it did, the graphics were embarrassing by comparison.
41
The UI looks like it was built with Twitter Bootstrap, which is a library that was written before most of you were born, and the 3D graphics aren't nearly as detailed as what Astra generated.
42
However, after actually playing the game for a few minutes, I quickly realized that the gameplay was far superior to what Astra had generated.
43
For one, the options for rocket customization are way more complex.
44
Claude provided way more knobs to turn, and made scientific calculations that make this feel more like a legit rocket simulator.
45
But then when it came to gameplay, the game was also just more fun, with a bunch of different possibilities for success or failure, and cooler animations when your rocket explodes.
46
But the big test was, which game do my kids prefer?
47
Well, this actually ended in a split decision, with the three-year-old preferring the more simplistic Astra game, with the eight-year-old preferring the more complex Fable game.
48
It's mostly subjective, but one thing's for sure, Astra's ability to generate 3D graphics has improved dramatically.
49
Just a couple months ago back in July, I had GPT Soul generate an exploded view of a mechanical watch, and the end result was a pile of useless garbage.
50
But when I re-ran the prompt again yesterday, the end result was this beautiful diagram that likely would have taken a 3D designer hundreds of hours to produce.
51
And this actually terrifies me, because it's going to lead to a new wave of slop on YouTube of people copying channels like Jared Owen, and other people who make 3D explainer videos.
52
Videos like this used to be what we would call high effort, and might require hundreds of hours of 3D design work in Blender.
53
Unfortunately, that moat no longer exists, and the rise of 3D slop is going to be the next big thing that makes the internet suck even more.
54
But we still haven't answered the question, is Astra actually AGI?
55
Well, as you know, the only way to find out is to see
56
if it can build horse tender without making any mistakes.
57
It took 21 minutes to run the prompt, and this was the final result, a design that looks surprisingly similar to one made by Fable a few months ago.
58
However, this design is noticeably cleaner and more elegant, and after spending many, many hours going through every single line of code looking for a mistake, I wasn't able to find a single one.
59
I felt like I was Antonio Salieri reading the flawless music of Mozart.
60
Here again was the very voice of God.
61
And then I realized that can only mean one thing.
62
Jensen was not Wong.
63
AGI has been achieved.
64
Or wait, actually, hold on.
65
Wait a minute.
66
This carrot is a few pixels off.
67
The false alarm, this is just another dumb AI model.
68
If you want to build a seriously good UI, you need to use Mobbin, the sponsor of today's video.
69
It lets your coding agent study more than 600,000 real UI screens before it designs anything.
70
I've already been using Mobbin for over five years because it shows you complete user flows from thousands of applications.
71
And its MCP server now puts that entire library inside CloudCode, Cursor, Codex, and all the others.
72
So instead of asking for a settings page and getting the same purple gradient vibes lop, you start by telling your agent to study how the best apps built that complete user flow.
73
It'll use Mobbin to gather the references, build a visual report of the patterns they share, then use those findings to recreate it and adapt it to your app.
74
Every result points back to its original screen, so you can check the source before trusting a design hallucination.
75
Try Mobbin today and get a 20% discount at the link below.
76
This has been The Code Report, thanks for watching, and I will see you in the next one.

Uygulamayı İndir

Akıcı konuşmak için ihtiyacınız olan her şey

AI TelaffuzHer cümleyi puanla
IPA AlıştırmasıHer sesi ustalaştır
Kelime BilgisiKelime bankanızı oluşturun
Kelime OyunuOynarken öğrenin

Aynı Kanal

FOR YOU

Video Öner

Bu dersin kelimeleri ve konuşma notları

Bu C1 seviyesindeki konuşma dersi “I built the same game with Astra and Fable 5.1... only one was fun” videosuna dayanıyor. En çok tekrarlanan kelimeler: Astra, graphic, rocket, Agi, Fable. Bu videoda gölgeleme çalışması için 76 cümle ve 1288 kelime var. Konuşma bölümü 6:06 sürüyor. Konuşmacı hızlı konuşuyor, dakikada yaklaşık 211 kelime; bu yüzden birbirine bağlanan ve zayıflayan sesler duyacaksınız. Kelimelerin yalnızca %78’i İngilizcede en sık kullanılan 3.000 kelime arasında, bu yüzden kelime dağarcığı zorlayıcı.

Bu videodaki önemli kelimeler

Videodaki en ileri düzey 15 kelime, telaffuzu ve anlamıyla:

KelimeTelaffuzAnlam
benchmark isim/ˈbɛn(t)ʃmɑːk/mihenk taşı
orbit isim/ˈɔɹ.bɪt/yörünge
terrify fiil/ˈtɛɹɪfaɪ/dehşete düşürmek
explode fiil/ɪkˈsploʊd/patlamak
embarrass fiil/ɪmˈbæɹəs/rezil etmek
hallucination isim/həˌluːsɪˈneɪʃən/sanrı, halüsinasyon
memorize fiil/ˈmɛm.əˌɹaɪ̯z/ezberlemek
flawless sıfat/ˈflɔləs/kusursuz
carrot isim/ˈkæɹət/havuç
obsolete sıfat/ˈɑbsəlit/eskimiş
harness fiil/ˈhɑɹ.nəs/koşmak, koşum takmak
pixel isim/ˈpɪk.səl/piksel, gözek
calculation isim/ˌkælkjuˈleɪʃn̩/hesaplama
subjective sıfat/səbˈd͡ʒɛktɪv/öznel
diagram isim/ˈdaɪ.ə.ɡɹæm/şema

Duyacağınız deyimsel fiiller

KelimeAnlam
find out fiilanlamak, ortaya çıkarmak

Bu videodaki dil bilgisi

Konuşmacının en çok kullandığı yapılar, videodaki sözcüklerin aynısıyla:

YapıVideoda
Present perfect have/has + fiilin üçüncü hâli — geçmişte olan ama şimdi de önemli olan bir eylemhas arrived · has been called · I've seen
Edilgen yapı be + fiilin üçüncü hâli — kimin yaptığı değil, ne olduğu önemliwas trained · has been called · was designed
İlgi cümlecikleri who / which + cümle — bir kişi ya da şey hakkında ek bilgiman who in · benchmark, which was · Bootstrap, which is

Dikkat edilecek telaffuzlar

Konuşmacı I've, wasn't, we'll gibi kısaltılmış biçimleri 14 kez kullanıyor. Bunları duyduğunuz gibi kısa söyleyin.

  • “sh” ve “zh” sesleri: benchmark /ˈbɛn(t)ʃmɑːk/, hallucination /həˌluːsɪˈneɪʃən/, calculation /ˌkælkjuˈleɪʃn̩/
  • Uzun kelimeler — vurguyu doğru yere koyun: simulator /ˈsɪmjəˌleɪtɚ/, generalize /ˈd͡ʒɛn.(ə.)ɹə.laɪz/, hallucination /həˌluːsɪˈneɪʃən/, surprisingly /səˈpɹaɪzɪŋli/

Türkçe konuşanların zorlandığı sesler:

  • Kelime başındaki ünsüz kümesi — araya ünlü eklemeyin: slop /slɑp/, prompt /pɹɑmpt/, gradient /ˈɡɹeɪdiənt/, flawless /ˈflɔləs/, sponsor /ˈspɒn.səː/
  • /æ/ — “e”den daha açık: embarrass /ɪmˈbæɹəs/, handcraft /ˈhændˌkɹæft/, carrot /ˈkæɹət/, calculation /ˌkælkjuˈleɪʃn̩/, diagram /ˈdaɪ.ə.ɡɹæm/

Bu videoyla nasıl çalışılır

  1. Videonun tamamını konuşmadan bir kez dinleyin ve bilmediğiniz kelimeleri not edin.
  2. 0,75× hızla başlayın, cümle cümle tekrar edin ve kolaylaşınca normal hıza dönün.
  3. Kendinizi kaydedin ve orijinaliyle karşılaştırın; benchmark, orbit, terrify gibi kelimelere özellikle dikkat edin.

Gölgeleme Tekniği Nedir?

Gölgeleme, başlangıçta profesyonel tercüman eğitimi için geliştirilen ve çok dilli Dr. Alexander Arguelles tarafından popüler hale getirilen, bilim destekli bir dil öğrenme tekniğidir. Yöntem basit ama güçlüdür: ana dili İngilizce olan bir sesi dinler ve hemen yüksek sesle tekrar edersiniz — konuşmacıyı 1-2 saniye gecikmeyle takip eden bir gölge gibi. Pasif dinleme veya dilbilgisi alıştırmalarının aksine, gölgeleme beyninizi ve ağız kaslarınızı gerçek konuşma kalıplarını eşzamanlı olarak işlemeye ve yeniden üretmeye zorlar. Araştırmalar, telaffuz doğruluğu, tonlama, ritim, bağlı konuşma, dinleme anlama ve konuşma akıcılığını önemli ölçüde geliştirdiğini göstermektedir — bu da onu IELTS Konuşma hazırlığı ve gerçek dünya İngilizce iletişimi için en etkili yöntemlerden biri yapar.

Shadowing tekniği: adım adım eksiksiz rehberi okuyun →