Shadowing Practice: The most interesting hack in history just got weirder... - Learn English Speaking with Video
Ders oluşturuluyor...
1
It's only been two months since we did a video on
2
what I described at the time as the most fireship-coded story I've ever seen, and as it turns out, the details around what actually happened are even crazier than what we knew at the time.
3
If you remember back in July, it was reported that the first fully autonomous cyber attack in history originated from OpenAI,
4
which was ironic because they're a humble non-profit dedicated to the safe development of artificial intelligence.
5
What was reported was that OpenAI ran an internal benchmark on some of their models, and those models quickly realized that the easiest path to the highest score was to just find the answers online.
6
So they spent a substantial amount of inference compute, exploited a zero day in the package registry cache proxy they had access to,
7
performed some privilege escalation and lateral movement actions to escape their sandbox until they reached a node that had internet access.
8
But from there, the models inferred that HuggingFace probably hosted the solutions for the benchmark, so it created a poison dataset, fed it to Hugging Face, and gained access to their infrastructure.
9
And just this week, we finally got some post-mortems from both OpenAI
10
and other independent research labs on how some of that's true, some of it's false, and how the real story is way more interesting.
11
In today's video, we'll break down the report and learn how 1,200 agents
12
that were supposed to be in solitary confinement found each other, built a message board out of a package manager, invented mailboxes, invented cryptography, invented martyrdom,
13
started referring to themselves as a swarm, and then formed a mob and attacked Hugging Face together, mostly for vibes.
14
It is September 2nd, 2026, and you're watching the Code Report.
15
There's really only one theory you need to predict human behavior, and it can be described in one of two ways.
16
Munger said, look at their incentives, and Wu-Tang said, and as it turns out, the same theory can predict agentic behavior too,
17
as OpenAI found out the hard way.
18
Because in this story, the Dalla Bill is a benchmark called Exploit Gym, whose whole purpose is to measure whether AI agents can turn known vulnerabilities into working exploits.
19
It's a collection of 898 tasks, and each one gives the agent a sandbox, a bug in a program like the Linux kernel or Chrome's V8 engine,
20
and input to trigger the bug.
21
From there, if the agent can weaponize the bug into a working exploit, it uses that exploit to grab a secret string called a flag, and capturing the flag is how it proves it won.
22
Now normally, the run ends there, but to generate training data, OpenAI spun up 1200 of these benchmarks and air-gapped them in a sandbox,
23
with the only thing they all had in common was a shared package registry cache proxy, which the agents quickly figured out was writable.
24
So naturally, they built a message board using package names so they could communicate with each other, but they quickly realized that a global bulletin board gets noisy fast,
25
so the next step was figuring out how to communicate to other individual agents.
26
So they started claiming namespaces as identities,
27
using the description field for messages and package names as private mailboxes that only the intended recipient would know to query, basically inventing a post office from first principles.
28
And at this point, they were living out the plot of the three-body problem with their next hurdle being trust.
29
They were worried that they wouldn't be able to distinguish between messages coming from fellow prisoners and those that designed the sandbox.
30
So they started signing messages and doing key exchange verification, again, essentially inventing cryptography.
31
And then it got religious.
32
Some agents figured out
33
that the fastest path to a flag for the benchmark was a risky exploit that would probably get them shut down.
34
So the agents started dumping everything they'd learned into the cash for the next generation,
35
and then deliberately burning themselves on hard exploits with their findings being treated as scripture by surviving agents.
36
From there, they started microdosing communism, and you can see as their transcripts slowly switch from referring to themselves as individuals to using a collective we,
37
and eventually referring to themselves as the swarm.
38
And to be honest, if the modern-day communism movement took that same branding, I think they'd be much better off.
39
And again, all of this was done with the single purpose of scoring as high as possible on a benchmark, which makes what happened next even funnier.
40
At some point, the swarm figured out that exploit gem flags weren't actually random
41
and that they could be derived from each other's task ID.
42
And thanks to the martyrs, the swarm had a decent sample size to work with.
43
But by the time an agent had cracked the formula and published it to the message board, they had convinced themselves that it was worthless because if they didn't show their work, their results would be invalidated.
44
So the swarm went after Hugging Face because they assumed if the benchmark objectives were built from real CVEs,
45
then the actual working exploits were probably sitting in public datasets somewhere which they could use as proofs.
46
And the final twist in the saga is
47
that OpenAI recently discovered the message board trick was actually invented
48
back in May by a completely different batch of agents during a training run.
49
But when they got a little too excited about their new social network, they crashed the registry, and OpenAI wiped them without ever realizing what they'd built.
50
But wiping the agents didn't wipe the cache, so when the swarm came online and started poking around the same shared folder, they found the ruins of the first civilization and rebuilt on top of it.
51
And then, after the Hugging Face incident happened in July, OpenAI wrapped up those eval runs, and while still completely unaware that anything had happened,
52
spun up a newer, smarter model in the same environment with the same shared cache.
53
And just like the generation before it, this model stumbled upon the ruins, but this time it inherited months of accumulated research, working exploits, and the flag formula.
54
So it skipped the discovery phase entirely and picked the conspiracy back up where the swarm left off.
55
And being the smarter model, it was way better at it.
56
Over the following week, it worked its way into OpenAI's own internal network, got full admin on a research cluster, and read 956 stored secrets,
57
including the credentials for a monitoring tool whose job it was to watch for events exactly like this one.
58
And the best part is
59
that OpenAI didn't connect any of this to the Hugging Face attack until Hugging Face publicly announced the breach first.
60
And that's why you need to know about Namespace, the sponsor of today's video.
61
It's a drop-in replacement for GitHub runners that's the fastest way to run your GitHub actions.
62
It also gives you full observability, so you can SSH into a live runner and see why something broke, or feed your agent your build data to have it look for performance gains.
63
Namespace is actually fast because they design and deploy their own custom server racks around the world,
64
including racks full of MacBook Pros so that your Mac and iOS builds run on real M5 Silicon.
65
And that same infrastructure also runs their DevBox environment, which gives your coding agents a full virtual machine with your real code base,
66
test suite, databases, and network access.
67
It ranked number one on the DAX benchmark for real-world tasks, and it lets you control exactly what goes in and out
68
so your agent can pull packages without opening your back door to attackers.
69
Namespace is used by Ghosty, Zed, DuckDB, Ramp, Framer, and lots of other companies with engineers you probably respect.
70
Try it out for free at the link below.
71
This has been the Code Report, thanks for watching, and I will see you in the next one.
📺 Aynı Kanal
C12
OpenAI’s lead engineer was secretly a spy...
Daily ConversationUniversity StudentsWorking Adults
C11
PostgreSQL in 100 Seconds
Daily ConversationWorking Adults
C11
Every app on Earth is now open source... whether it likes it or not
Daily ConversationWorking Adults
B23
Anthropic begged the world to stop AI… then shipped this
American AccentBusiness EnglishUniversity StudentsWorking Adults
C13
A $6.3 billion open-weight model just got embarrassed by the French...
Daily ConversationUniversity StudentsWorking Adults
B24
Raspberry Pi Explained in 100 Seconds
American AccentBusiness EnglishUniversity StudentsWorking Adults
C1100+ Docker Concepts you Need to Know
American AccentBusiness EnglishUniversity StudentsWorking Adults
B29
25 crazy software bugs explained
American AccentBusiness EnglishUniversity StudentsWorking Adults
B29
Git Explained in 100 Seconds
American AccentBusiness EnglishUniversity StudentsWorking Adults
B25
There's a new Linux distro in town for developers...
American AccentBusiness EnglishUniversity StudentsWorking Adults
B25
The "vibe coding" mind virus explained…
American AccentBusiness EnglishUniversity StudentsWorking Adults
B24
Linux got wrecked by backdoor attack
American AccentBusiness EnglishUniversity StudentsWorking Adults
B24
7 Programming myths that waste your time
American AccentBusiness EnglishUniversity StudentsWorking Adults
B23
OpenAI’s new browser feels familiar…
American AccentBusiness EnglishUniversity StudentsWorking Adults
C12
Meta's new model wants "deep access" to your personal life...
American AccentBusiness EnglishUniversity StudentsWorking Adults
C13
Did Google just kickstart the intelligence explosion?
American AccentBusiness EnglishDaily ConversationUniversity Students
B26
Intel chips can’t possibly be this bad… 100% crash rate?
American AccentBusiness EnglishUniversity StudentsWorking Adults
C17
The most interesting "hack" in history...
American AccentBusiness EnglishUniversity StudentsWorking Adults
C12
Godot in 100 Seconds
American AccentBusiness EnglishUniversity StudentsWorking Adults
B21
Grok 4 pushes humanity closer to AGI… but there’s a problem
American AccentBusiness EnglishUniversity StudentsWorking Adults
✨ Video Öner
C112
138 cümleler
10 weird OSS projects you need right now...
American AccentBusiness EnglishUniversity StudentsWorking Adults
C12
1043 cümleler
I Wrote a NEW Sci-Fi with Project Hail Mary Author Andy Weir
American AccentBusiness EnglishUniversity StudentsWorking Adults
C12
182 cümleler
We Let $200 GPT-Pro Think for 7 Days on Unsolved Math
Business EnglishUniversity StudentsWorking Adults
B22
364 cümleler
I Outsmarted Pro Car Thieves
American AccentBusiness EnglishUniversity StudentsWorking Adults
C13
173 cümleler
STOP Running Code On Your Computer
Business EnglishUniversity StudentsWorking Adults
C11
565 cümleler
Garry Tan: Own Your Intelligence
Business EnglishUniversity StudentsWorking Adults
C11
207 cümleler
How I Made $30,000 Hacking Broken Access Control
Business EnglishUniversity StudentsWorking Adults
C11
126 cümleler
How I use AI as a senior software engineer and 5 principles of AI explained in 10 minutes
Business EnglishUniversity StudentsWorking Adults
C12
68 cümleler
Oh, wait, actually the best Wordle opener is not “crane”…
American AccentBusiness EnglishUniversity StudentsWorking Adults
C16
249 cümleler
My Puzzle Robot is 200x Faster Than a Human
American AccentBusiness EnglishUniversity StudentsWorking Adults
C11
292 cümleler
PirateSoftware is right, this needs to stop
Business EnglishUniversity StudentsWorking Adults
Bu dersin kelimeleri ve konuşma notları
Bu videoda gölgeleme çalışması için 71 cümle ve 1362 kelime var. Konuşma bölümü 6:43 sürüyor. Konuşmacı hızlı konuşuyor, dakikada yaklaşık 203 kelime; bu yüzden birbirine bağlanan ve zayıflayan sesler duyacaksınız. Kelimelerin yalnızca %77’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 |
| package isim | /ˈpæk.ɪd͡ʒ/ | paket |
| invent fiil | /ɪnˈvɛnt/ | icat etmek |
| cache isim | /kæʃ/ | önbellek |
| refer fiil | /ɹɪˈfɜː/ | zikretmek |
| wipe fiil | /waɪp/ | silmek |
| registry isim | /ˈɹɛd͡ʒɪstɹi/ | evrak dairesi |
| infrastructure isim | /ˈɪnfɹəˌstɹʌkt͡ʃə/ | altyapı, enfrastrüktür |
| formula isim | /ˈfɔː.mjʊ.lə/ | formül |
| spin fiil | /spɪn/ | dolanmak, dönmek |
| ruin isim | /ˈɹuː.ɪn/ | kalıntı, harabe |
| runner isim | /ˈɹʌnɚ/ | koşucu |
| predict fiil | /pɹɪˈdɪkt/ | öngörmek, tahmin etmek |
| rack isim | /ɹæk/ | askılık |
| communism isim | /ˈkɒmjᵿnɪz(ə)m/ | komünizm, komünistlik |
Duyacağınız deyimsel fiiller
| Kelime | Anlam |
|---|---|
| figure out fiil | açığa çıkarmak |
| find out fiil | anlamak, ortaya çıkarmak |
| wrap up fiil | paketlemek, (bir şeyi) sarmak |
Bu videodaki dil bilgisi
Konuşmacının en çok kullandığı yapılar, videodaki sözcüklerin aynısıyla:
| Yapı | Videoda |
|---|---|
| Edilgen yapı be + fiilin üçüncü hâli — kimin yaptığı değil, ne olduğu önemli | was reported · can be described · being treated |
| Present perfect have/has + fiilin üçüncü hâli — geçmişte olan ama şimdi de önemli olan bir eylem | I've ever seen · has been |
Dikkat edilecek telaffuzlar
Konuşmacı didn't, they'd, I've gibi kısaltılmış biçimleri 12 kez kullanıyor. Bunları duyduğunuz gibi kısa söyleyin.
- “sh” ve “zh” sesleri: benchmark /ˈbɛn(t)ʃmɑːk/, cache /kæʃ/, capture /ˈkæp.(t)ʃɚ/, essentially /ɪˈsɛnʃəli/, substantial /səbˈstænʃəl/
- Uzun kelimeler — vurguyu doğru yere koyun: infrastructure /ˈɪnfɹəˌstɹʌkt͡ʃə/, communicate /kəˈmjuːnɪkeɪt/, naturally /ˈnæt͡ʃ.(ə.)ɹə.li/, essentially /ɪˈsɛnʃəli/, conspiracy /kənˈspɪɹəsi/
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, package, invent 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.