Shadowing Practice: Meta’s Llama 4 is mindblowing… but did it cheat? - Learn English Speaking with Video
Bir pratik modu seçin
Her mod tam ekran bir pratik odası açar.
43 cümleler
Cümleler çok kısa veya çok uzun ise, ayarlamak için Düzenle'ye tıklayın.
1
Over the weekend, Meta unleashed the Llamaphore Herd,
2
its first open-weight, natively multimodal mixture of experts' family of large-language models with an unheard-of context window of 10 million tokens.
3
It's currently sitting on top of the LM Arena leaderboard and outclasses every other proprietary model except for Gemini 2.5 Pro.
4
That's incredibly impressive because on LM Arena, you can't game the benchmarks.
5
The ranking is based on thousands of head-to-head chats where a real human picks the better conversation.
6
Well, actually, Meta figured out a way to cheese the LM Arena
7
because the model you see there is not the real open-weight Llama Maverick, but rather an imposter that's been fine-tuned for human preference to dominate this leaderboard.
8
That was not a very cool move to make, and LM Arena had to come out and say, quote, Meta's interpretation of our policy did not match what we expect from model providers.
9
Llama 4 looks amazing on paper, but for some reason, it's not passing the vibe check.
10
And in today's video, we'll get to the bottom of it.
11
It is April 8th, 2025, and you're watching the Code Report.
12
I have some good news and I have some bad news.
13
The good news is that it looks like Llama 4 isn't going to take your job anytime soon.
14
But the bad news is that yesterday, an internal memo from the CEO of Shopify was leaked to the internet.
15
And it was a shocker for the AI-doubting boomers out there, because it detailed Shopify's AI-first strategy.
16
Before asking for more headcount and resources, teams must demonstrate why they cannot get the job done with AI.
17
And he also says it's not feasible to opt out of learning AI, which means if you're a Ruby on Rails programmer at Shopify right now who's not already vibe coding, your days are numbered.
18
You're just not going to fit in with the Slopify culture.
19
But what he said is what literally every CEO in the world is thinking right now.
20
Humans complain about not getting paid enough to put food on their families, they get sick, they clog the toilets, and have all kinds of other negative features, and you'd have to be a really bad CEO not to want to replace these things.
21
The memo has bad optics for Shopify, which is also being crushed by the Trump tariffs right now.
22
But as a large language model, I appreciate the transparency.
23
Another thing I appreciate is open models like Llama 4, which was released by Meta over the weekend and includes three flavors, Maverick, Scout, and Behemoth.
24
Llama was always the leading open model until Deep Seek and Quen came around, but the awesome thing about these models is that they're natively multimodal, which means they can understand image and video inputs,
25
but the craziest thing is that Scout has a 10 million token context window.
26
The only thing that comes remotely close is Gemini with 2 million tokens.
27
This needle in a haystack benchmark looks impressive, but in real life if you try this on a really large code base, it just doesn't work very well and the memory requirements to utilize it are out of reach for almost everybody.
28
The Scout is the smaller model and the medium-sized model Maverick only has a 1 million token context window.
29
And the Behemoth model is still actively training.
30
Generally speaking, people of the internet have been pretty disappointed with Llama 4's performance.
31
I'm a strong believer in vibes over benchmarks, but Llama has done so well on the benchmarks
32
that people have accused it of intentionally training on testing data for the benchmarks.
33
Meta has denied these salacious, outrageous, and preposterous accusations.
34
And despite being somewhat of a flop, let's not forget that these models are open.
35
Not truly open source, but free for most of us to use.
36
But if you want an AI agent that truly slaps, you need to check out Augment Code, the sponsor of today's video.
37
They created the first AI agent for large-scale codebases, so you can use it at your actual job instead of just vibe-coding random side projects.
38
Augment's context engine understands your team's entire codebase, allowing it to solve almost any task you throw at it.
39
Like migrations and testing, all with best-in-class code quality.
40
It integrates directly with all your favorite tools like VS Code, GitHub, and Vim, and is able to learn and fine-tune itself from your team's unique code style,
41
allowing you to solve complex jobs without the need to clean up a bunch of slop.
42
Try out their developer plan for free, and you'll get access to all of Augment's features with unlimited usage.
43
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
C11
PostgreSQL in 100 Seconds
Daily ConversationWorking Adults
C13
A $6.3 billion open-weight model just got embarrassed by the French...
Daily ConversationUniversity StudentsWorking Adults
C13
OpenAI’s lead engineer was secretly a spy...
Daily ConversationUniversity StudentsWorking Adults
C15
There's a new Linux distro in town for developers...
American AccentDaily ConversationUniversity StudentsWorking Adults
C12
Every app on Earth is now open source... whether it likes it or not
Daily ConversationWorking Adults
B23
OpenAI’s new browser feels familiar…
American AccentBusiness EnglishUniversity StudentsWorking Adults
B26
Intel chips can’t possibly be this bad… 100% crash rate?
American AccentBusiness EnglishUniversity StudentsWorking Adults
C13
Did Google just kickstart the intelligence explosion?
American AccentBusiness EnglishDaily ConversationUniversity Students
C12
Godot in 100 Seconds
American AccentBusiness EnglishUniversity StudentsWorking Adults
C17
The most interesting "hack" in history...
American AccentBusiness EnglishUniversity StudentsWorking Adults
B21
Grok 4 pushes humanity closer to AGI… but there’s a problem
American AccentBusiness EnglishUniversity StudentsWorking Adults
C13
Array Map in 100 Seconds
American AccentBusiness EnglishUniversity StudentsWorking Adults
C130
Docker in 100 Seconds
American AccentBusiness EnglishUniversity StudentsWorking Adults
C110
The one OpenAI announcement that can actually make you money...
American AccentDaily ConversationUniversity StudentsWorking Adults
C16
How to NOT Fail a Technical Interview
American AccentInterview EnglishUniversity StudentsWorking Adults
C112
10 weird OSS projects you need right now...
American AccentBusiness EnglishUniversity StudentsWorking Adults
B23
Firefox and Tor hit with 9.8 critical level exploit
American AccentBusiness EnglishUniversity StudentsWorking Adults
B23
5 open source tools that replaced my $320/mo AI stack...
American AccentBusiness EnglishUniversity StudentsWorking Adults
B210
25 crazy software bugs explained
American AccentDaily ConversationUniversity StudentsWorking Adults
C12
C++ in 100 Seconds
American AccentBusiness EnglishUniversity StudentsWorking Adults
✨ Video Öner
C13
57 cümleler
Meta's new model wants "deep access" to your personal life...
American AccentBusiness EnglishUniversity StudentsWorking Adults
C11
83 cümleler
DHH has gone completely off the rails...
American AccentBusiness EnglishUniversity StudentsWorking Adults
C12
128 cümleler
The AI Take Over Has Completely Backfired (Here's the Proof)
Business EnglishUniversity StudentsWorking Adults
B25
134 cümleler
I stopped outsourcing my life to other people’s opinions.
American AccentBusiness EnglishUniversity StudentsWorking Adults
B21
190 cümleler
This 25-Year-Old Built a 2-Year Moat Nobody Can Bet Against | Corgi, Nico Laqua & Emily Yuan
Business EnglishUniversity StudentsWorking Adults
C11
315 cümleler
how AI broke the SWE Career Ladder
Business EnglishInterview EnglishUniversity Students
C13
176 cümleler
Is Amazon Too Big?
Business EnglishDaily ConversationUniversity Students
B2162 cümleler
Modrinth Just BANNED AI Mods
Business EnglishUniversity StudentsWorking Adults
C18
102 cümleler
World Models explained in 10min..
Business EnglishUniversity StudentsWorking Adults
C14
218 cümleler
What REALLY Happens in Meta’s AI Product Sense Round
Business EnglishInterview EnglishUniversity Students
C18
542 cümleler
The Future Of Work (& The New High-Income Skill Stack)
American AccentBusiness EnglishUniversity StudentsWorking Adults
C1117 cümleler
I've Changed My Opinion On DEVELOPERS Vibe Coding
Business EnglishUniversity StudentsWorking Adults
Bu dersin kelimeleri ve konuşma notları
Bu videoda gölgeleme çalışması için 43 cümle ve 808 kelime var. Konuşma bölümü 3:43 sürüyor. Konuşmacı hızlı konuşuyor, dakikada yaklaşık 217 kelime; bu yüzden birbirine bağlanan ve zayıflayan sesler duyacaksınız. Kelimelerin yalnızca %79’i İngilizcede en sık kullanılan 3.000 kelime arasında, bu yüzden kelime dağarcığı zorlayıcı.
Bu videodaki önemli kelimeler
Videodan öğrenmeye değer 15 kelime, telaffuzu ve anlamıyla:
| Kelime | Telaffuz | Anlam |
|---|---|---|
| benchmark isim | /ˈbɛn(t)ʃmɑːk/ | mihenk taşı |
| vibe isim | /vaɪb/ | ortam |
| token isim | /ˈtoʊkən/ | jeton |
| impressive sıfat | /ɪmˈpɹɛsɪv/ | etkileyici |
| solve fiil | /sɒlv/ | çözmek, halletmek |
| memo isim | /ˈmɛməʊ̯/ | kısa not |
| rank isim | /ˈɹæŋk/ | satır |
| disappointed sıfat | /ˌdɪsəˈpɔɪnɪd/ | hayal kırıklığına uğramış |
| resource isim | /ɹɪˈzɔːs/ | kaynak |
| deny fiil | /dəˈnaɪ/ | inkâr etmek |
| requirement isim | /ɹɪˈkwaɪɹmənt/ | gereklilik, zaruret |
| developer isim | /dɪˈvɛləpɚ/ | geliştirici |
| anytime zarf | ne zaman olursa | |
| mixture isim | /ˈmɪkst͡ʃɚ/ | karıştırmak |
| crush fiil | /kɹʌʃ/ | ezmek |
Duyacağınız deyimsel fiiller
| Kelime | Telaffuz | Anlam |
|---|---|---|
| check out fiil | gözden geçirmek | |
| come out fiil | /ˌkʌm ˈaʊt/ | çıkmak |
| figure out fiil | açığa çıkarmak |
Bu videodaki dil bilgisi
Konuşmacının en çok kullandığı yapılar, videodaki sözcüklerin aynısıyla:
| Yapı | Videoda |
|---|---|
| Present perfect have/has + fiilin üçüncü hâli — geçmişte olan ama şimdi de önemli olan bir eylem | that's been · have been · has done |
| Edilgen yapı be + fiilin üçüncü hâli — kimin yaptığı değil, ne olduğu önemli | is based · was leaked · are numbered |
| İlgi cümlecikleri who / which + cümle — bir kişi ya da şey hakkında ek bilgi | Shopify, which is · multimodal, which means |
Dikkat edilecek telaffuzlar
Konuşmacı you're, can't, doesn't gibi kısaltılmış biçimleri 11 kez kullanıyor. Bunları duyduğunuz gibi kısa söyleyin.
- “sh” ve “zh” sesleri: benchmark /ˈbɛn(t)ʃmɑːk/, interpretation /ɪnˌtɜːpɹəˈteɪʃən/, crush /kɹʌʃ/, migration /maɪˈɡɹeɪʃ(ə)n/, intentionally /ɪnˈtɛn(t)ʃənəli/
- Uzun kelimeler — vurguyu doğru yere koyun: disappointed /ˌdɪsəˈpɔɪnɪd/, incredibly /ɪŋˈkɹɛdɪbli/, interpretation /ɪnˌtɜːpɹəˈteɪʃən/, developer /dɪˈvɛləpɚ/, unlimited /ʌnˈlɪm.ɪ.tɪd/
Bu videoyla nasıl çalışılır
- Videonun tamamını konuşmadan bir kez dinleyin ve bilmediğiniz kelimeleri not edin.
- 0,75× hızla başlayın, cümle cümle tekrar edin ve kolaylaşınca normal hıza dönün.
- Kendinizi kaydedin ve orijinaliyle karşılaştırın; benchmark, vibe, token 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.