シャドーイング練習: 5 open source tools that replaced my $320/mo AI stack... - 動画で英語スピーキングを学ぶ
レッスンを作成中...
1
Recently, I did some math, and it made me realize how broken the world is.
2
A cursor, $20.
3
Claude Max, $100.
4
GPT Pro, another $100.
5
Gemini Ultra, another $100.
6
Not to mention 11 Labs, DeepSeq, and all the API keys I signed up for two years ago and forgot about.
7
My AI addiction got so expensive that I had to quit alcohol and Zin.
8
And I'm not the only one, because alcohol sales in the United States are currently sitting at historic lows.
9
And Big AI is the one to blame for this.
10
But that was my wake-up call, and since then, I've cancelled all these subscriptions, and now self-host the ultimate AI stack for developers that's not only cheaper, but far more productive.
11
In today's video, we'll look at a bunch of free and open-source projects you can run on your own server.
12
We'll make them work together, while still having the option to tap into the intelligence of big models like Claude and GPT Sol.
13
It is September 7th, 2026, and you're watching The Code Report.
14
The first tool we need to talk about is OLAMA, because every AI stack first needs a model.
15
For most people, this means sending your proprietary code to a trillion dollar corporation and trusting them to keep it totally safe, or you can use OLAMA and do everything locally.
16
I've talked about this tool many other times on the channel, and essentially it's like Docker for large language models.
17
It gives you a simple command line interface and API for downloading and running models on your own machine.
18
This is great if you want to try out the latest Chinese models or any other open weight models, and what's even better is that all your prompts stay private and the inference cost is zero,
19
which means the model continues to work even after your credit card is declined.
20
The big problem, though, is that you probably don't own the hardware to run anything close to state-of-the-art.
21
The small models will run almost anywhere, but running a frontier-sized model would require a small data center, and that's a big problem if you're a Vibe engineer who needs to write top-tier slot.
22
Luckily, there's a self-hostable solution to this called 9Router, which is an AI tool that sits between your AI tools and dozens of different model providers through one local endpoint.
23
Instead of juggling nine different API keys, 9Router provides one door with an OpenAI compatible proxy that allows you to point everything through localhost.
24
But the thing that's really cool about 9Router is fallback tiers.
25
On tier one, you might have an existing subscription like Claude Max that you already pay for.
26
Then on tier two, you might have a cheap pay-per-token OpenAI model as a backup.
27
Then tier three has all of free providers like Chinese models, vertex trial credits, and so on.
28
That means if you max out Claude Max, it'll automatically roll over to the next tier without you having to do anything.
29
But in addition to that, 9Router also tracks usage and will compress your tool output to reduce token consumption, which will ultimately save you a bunch of money.
30
But if you're still eating billions of tokens per day, then you need to know about Headroom, which is a context compression layer for AI agents.
31
You ask AI to center a div, and to do that, it reads 50,000 lines of your package lock JSON file, then it evaporates an Olympic-sized swimming pool worth of water,
32
just to realize it needs to install Tailwind CSS.
33
Headroom sits between your application and the model provider,
34
and compresses everything from tool outputs to log files and any other useless chunks before it actually goes to the model, which would be billable input tokens.
35
And one clever design feature of this tool is that it's reversible.
36
The compressed content that ships to the model is cached on your local machine, which means if the model ever needs it, it can always retrieve it.
37
This sounds awesome, but at this point, you might be wondering, where do I deploy all this stuff?
38
Well, the answer, of course, is Hostinger, the sponsor of today's video.
39
Not only is it one of the most affordable places to host your own virtual private server, but they also have an entire Docker catalog built into the panel,
40
which means every single open source project I talk about in this video can be hosted there with a single click.
41
In fact, you could have all these tools running and working together on the same VPS.
42
Head over to hostinger.com slash fireship and use my coupon code to save a bunch of money spinning up your own VPS.
43
Once you have that done, the next tool you'll want to install there is Diffy.
44
Everything we've talked about so far is infrastructure, but now it's time to build an actual app that'll make us rich.
45
Instead of trying to engineer everything through prompts, Diffy is a visual builder that allows us to drag nodes on a canvas.
46
This has been a game changer for Horse Tinder and its AI matchmaking feature.
47
The app will send Diffy each horse's profile information, then a visual workflow retrieves compatible horses from the database, and uses a large language model to explain each match.
48
Like Thunder and Butternuts are a 94% match because they both enjoy trail rides and biting children.
49
Then the entire workflow is exposed as an API, so the front-end application can just call it whenever a horse swipes right.
50
Amazing, but building apps as a human became outdated in Q2 2026 after the release of open hands
51
which is an open source tool
52
that allows you to fire yourself this tool is a top performing autonomous coding agent on swebench verified
53
which is the benchmark where models fix real github issues instead of trying to build
54
and fix things just open up github issues
55
and let open hands do all the work essentially it gives
56
you a command center where you can self-host an army of ai agents
57
that are always on and working in the background and because Because it's running on your own virtual private server, you have the option to run it with OpenAI or Anthropic models,
58
or use the local LLMs that you installed earlier with OLAMA.
59
And now at this point, we have our own private AI stack that could build any type of software you can imagine.
60
But this is just the tip of the iceberg, and there's tons of other open source applications in Hostinger's Docker catalog that you can install with zero hassle.
61
Check out the link below
62
and use coupon code Fireship to get your own virtual private server on Hostinger up and running right now.
63
This has been the Code Report, thanks for watching, and I will see you in the next one.
📺 同じチャンネル
C11
PostgreSQL in 100 Seconds
Business EnglishUniversity StudentsWorking Adults
B23
Anthropic begged the world to stop AI… then shipped this
American AccentBusiness EnglishUniversity StudentsWorking Adults
B23
A $6.3 billion open-weight model just got embarrassed by the French...
Business EnglishUniversity StudentsWorking Adults
B22
7 Things No Programmer Ever Wants to Hear
American AccentBusiness EnglishWorking Adults
B21
80% of programmers are NOT happy… why?
American AccentBusiness EnglishUniversity StudentsWorking Adults
B24
Raspberry Pi Explained in 100 Seconds
American AccentBusiness EnglishUniversity StudentsWorking Adults
C13
Tragic mistake... Anthropic leaks Claude’s source code
American AccentBusiness EnglishUniversity StudentsWorking Adults
C1100+ Docker Concepts you Need to Know
American AccentBusiness EnglishUniversity StudentsWorking Adults
C13
The mystery is solved... and the answer is 40x cheaper than Claude
American AccentBusiness EnglishUniversity StudentsWorking Adults
B28
An ex-OpenAI researcher just deleted language from the LLM...
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
C115
Nvidia CUDA in 100 Seconds
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
✨ おすすめ動画
B21
341 文
I Tried PewDiePie's Odysseus AI So You Don't Have To
Business EnglishUniversity StudentsWorking Adults
B23
165 文
How I'd Learn AI From Scratch in 2026 (skip the useless 80%)
American AccentBusiness EnglishUniversity StudentsWorking Adults
B21
311 文
I bought Black Market AI Tokens on Chinese Amazon
Business EnglishUniversity StudentsWorking Adults
B21
283 文
The Gaming Market is Starting to Break.
British AccentBusiness EnglishUniversity StudentsWorking Adults
B21
179 文
I Self-Hosted for a Year... Here's What I'd Do Differently.
Business EnglishUniversity StudentsWorking Adults
B22
142 文
The Kurzgesagt Situation is Insane
Business EnglishUniversity StudentsWorking Adults
B21
76 文
Nvidia's New Laptops - RTX Spark
Business EnglishUniversity StudentsWorking Adults
B21
339 文
The (Overdue) Collapse of AI Layoffs (here's the proof)
Business EnglishInterview EnglishUniversity Students
B24
180 文
Is AI Doom Real... or Just Good Marketing?
Business EnglishUniversity StudentsWorking Adults
B21
329 文
Laziest Ways to Make Money with AI (For Beginners)
Business EnglishUniversity StudentsWorking Adults
このレッスンの語彙とスピーキングのポイント
このB2レベルのスピーキングレッスンは、動画「5 open source tools that replaced my $320/mo AI stack..」を教材にしています。 繰り返し出てくる語は次のとおりです：model, tool, tier, code, private。 この動画には、シャドーイング用の文が63文、単語が1161語あります。 音声の長さは5:22です。 話す速さは速く、1分あたり約217語です。音のつながりや弱く発音される音が多くなります。 英語の頻出3,000語に含まれる単語は80%だけなので、語彙は難しめです。
この動画の重要語彙
動画の中で特に難しい単語15語を、発音と意味つきで紹介します。
| 単語 | 発音 | 意味 |
|---|---|---|
| tier 名詞 | /ˈtɪɚ/ | 層, 階層 |
| token 名詞 | /ˈtoʊkən/ | トークン |
| compress 動詞 | /ˈkɑmpɹɛs/ | 圧縮する |
| stack 名詞 | /stæk/ | 塚 |
| install 動詞 | /ɪnˈstɔl/ | 導入する, インストールする |
| hosting 名詞 | /ˈhoʊstɪŋ/ | ホスティング |
| workflow 名詞 | /ˈwɝkfloʊ/ | ワークフロー |
| retrieve 動詞 | /ɹɪˈtɹiːv/ | 取り戻す |
| coupon 名詞 | /ˈkuːˌpɑn/ | クーポン |
| catalogue 名詞 | /ˈkæt.əˌlɔɡ/ | カタログ, 目録 |
| subscription 名詞 | /səbˈskɹɪpʃən/ | 定期購読, 購読 |
| cursor 名詞 | /ˈkɜːsə/ | カーソル |
| evaporate 動詞 | /ɪˈvæp.ə.ɹeɪt/ | 蒸発する, 揮発する |
| iceberg 名詞 | /ˈaɪsbɝɡ/ | 氷山 |
| juggling 名詞 | /ˈd͡ʒʌɡəlɪŋ/ | ジャグリング, ジャッグ |
動画に出てくる句動詞
| 単語 | 発音 | 意味 |
|---|---|---|
| check out 動詞 | 試験する, 検査する | |
| try out 動詞 | 試す, 試してみる | |
| wake up 動詞 | /ˌweɪk ˈʌp/ | 目覚める, 目を覚ます |
この動画の文法
話し手がよく使っている文型を、動画の実際の表現とともに紹介します。
| 文型 | 動画での表現 |
|---|---|
| 現在完了形 have/has + 過去分詞 — 過去の出来事が今も関係している | I've cancelled · I've talked · we've talked |
| 受動態 be + 過去分詞 — 誰がするかより、何が起きるかに焦点を当てる | is declined · is cached · can be hosted |
| 関係詞節 who / which + 節 — 人や物について情報を加える | consumption, which will · Headroom, which is · machine, which means |
注意したい発音
話し手はyou're, I've, we'llなど、短縮形や弱形を13回使っています。聞こえたとおりの短い形で発音しましょう。
- 「sh」と「zh」の音: subscription /səbˈskɹɪpʃən/, benchmark /ˈbɛn(t)ʃmɑːk/, cache /kæʃ/, compression /kəmˈpɹɛʃ.ən/, addiction /əˈdɪkˌʃən/
- 長い単語（アクセントの位置に注意）: compatible /kəmˈpæt.ə.bəl/, evaporate /ɪˈvæp.ə.ɹeɪt/, reversible /ɹəˈvɜː(ɹ)sɪbəl/, proprietary /pɹəˈpɹaɪ.ə.tə.ɹi/, autonomous /ɔˈtɑnəməs/
日本語話者が苦手な音：
- /r/ と /l/ の区別 — /l/ は舌先を歯茎につけ、/r/ はどこにもつけない: reversible /ɹəˈvɜː(ɹ)sɪbəl/, builder /ˈbɪl.dəɹ/
- /v/ — /b/ にならないように、上の歯を下唇に当てる: provider /pɹəˈvaɪ.də(ɹ)/, retrieve /ɹɪˈtɹiːv/, evaporate /ɪˈvæp.ə.ɹeɪt/, reversible /ɹəˈvɜː(ɹ)sɪbəl/, vertex /ˈvɝˌtɛks/
- /f/ — 「フ」ではなく、上の歯と下唇で出す: workflow /ˈwɝkfloʊ/, fallback /ˈfɔːl.bæk/, inference /ˈɪn.fə.ɹəns/, verify /ˈvɛɹɪfaɪ/, frontier /ˈfɹʌntɪə/
この動画での練習方法
- まず声を出さずに動画を最後まで聞き、知らない単語をメモします。
- まず0.75倍速で一文ずつシャドーイングし、慣れてきたら通常の速度に戻します。
- 自分の声を録音して元の音声と比べます。tier, token, compressなどの単語に特に注意しましょう。
シャドーイングとは？英語上達に効果的な理由
シャドーイング（Shadowing）は、もともとプロの通訳者養成プログラムで開発された言語学習法で、多言語習得者として知られるDr. Alexander Arguelles によって広く普及されました。方法はシンプルですが非常に効果的：ネイティブスピーカーの英語を聞きながら、1〜2秒の遅延で声に出してすぐに繰り返す——まるで「影（shadow）」のように話者を追いかけます。文法ドリルや受動的なリスニングと異なり、シャドーイングは脳と口の筋肉が同時にリアルタイムで英語を処理・再現することを強制します。研究により、発音精度、抑揚、リズム、連音、リスニング力、そして会話の流暢さが大幅に向上することが確認されています。IELTSスピーキング対策や自然な英語コミュニケーションを目指す方に特におすすめです。