Reo Ogusu retweeted
Today we launch BrowserCode, a full dev environment in a browser tab.
Share running projects instantly and experiment with agents in a isolated, safe playground.
What makes BrowserCode different? No account is required, and it's completely free.
labs.leaningtech.com/blog/an…
Reo Ogusu retweeted
Saying not knowing how to code gives you an advantage in building software (thanks to AI) is like saying not knowing anything about filmmaking gives you an advantage in making films (thanks to having a smartphone + apps to edit stuff)
Ignore this stuff and keep learning+building
Reo Ogusu retweeted
Not knowing how to code giving you an advantage is absolute nonsense.
The more you understand, the better your prompts, the better the feedback you give, the better product you ship.
What will change is that the intricacies of syntax, compilers, module systems, the finer details of type systems, won’t matter as much to everyone.
But you should absolutely understand how the pieces fit together. From syscall to pixels. Learn how data flows, because you’ll be able to secure your systems. Learn about performance, because you’ll be able to push your agent further. Learn about APIs, because they determine how to integrate systems. Learn about how systems fail, because you’ll be able to make reliable programs.
Reo Ogusu retweeted
Unpopular opinion:
Current code review tools just don’t make much sense for AI-generated code
When reviewing code I really want to know:
- The prompt made by the dev
- What corrections the other dev made to the code
- Clear marking of code AI-generated not changed by a human
Reo Ogusu retweeted
A few things I've noticed as all devs write code with AI.
When you write foundational / architectural code of a new project by hand, you "feel" the code pushing back if your abstraction isn't right. You feel when something is harder than it should be. The code is telling you it's not in the right shape. Good engineers are sensitive to this.
When you're using an LLM, you keep pushing right through this in a way that feels like you're making progress, and it may even be directionally correct in a sense, but the underlying foundation of it all is actually bad in a way that either kills progress of the LLM later as it buckles under the complexity it has created or destroys your ability to maintain the code long term.
Related to this, I see a general restlessness with just sitting and thinking about a problem for a while.
As I've been working on a new library here at Laravel, there have been days where it feels like I mainly just stare at my screen thinking about something. When Claude Code is at your fingertips, it's tempting to just start yapping into the terminal and watching code come out the other end. Again, directionally correct in some ways, but often doesn't land on the elegant solution that is waiting to be discovered.
Reo Ogusu retweeted
これ、いまだに誤解が多いので。
AIが進歩すれば、コードを「書ける」スキルは必要なくなっていきますが、そのかわり「読める」スキルの重要性は増します。
なぜか。
「理解を移譲することはできない」からです。
これを言ったのは、椅子などのデザインで有名なイームズです。
justinprather.com/eames-neve…
問題は、それを解こうとして取り組んだときにはじめて本質が見えてくる。だから、手を動かす部分は部下やAIに任せてもいいけれど、問題の本質についての理解を深めるためには、そのプロセスをしっかりとグリップしてなければいけない。
理解できていなければ、AIに的確な指示を出すこともできない。成果物の説明責任を果たすこともできない。それだけが唯一、人類に残された仕事になろうという時に。
AIは全力で使い倒し、そのプロセスを通じて学び、成長し、テストし、理解を深めることが大切です。
理解が深まる喜びにつながらないAIの使い方は、スロットマシーンを脳死状態で回し続けているのと同じだからです。
Reo Ogusu retweeted
Do you like aviation and games? We have the perfect match for you - Skycards a game from Flightradar24. Download now from
skycards.app and join thousands of players already playing the game.
Reo Ogusu retweeted
Quitting programming as a career right now because of LLMs would be like quitting carpentry as a career thanks to the invention of the table saw.
Reo Ogusu retweeted
. @hwchase17 I've resisted dumping on @langchain publically until now (despite how easy it would be) but if you're going to start publishing BS like this, I'll stop being so restrained:
* LangSmith caused a well known AI company to pivot away from Python because its tracing mess hung for 500ms on every function call.
* LangChain is blocked in at least one major public tech company for security reasons.
It's pretty brave of you to start referring to other people's libraries as "not really production ready".
Pick a fight with @OpenAI if you like, but leave @pydantic out of it.
OpenAI recently released a guide on building agents which contains some misguided takes
There's a lot of FUD, confusion, hype, and noise around agents
I wrote a blog on how to think about agent frameworks. Includes:
Background Info
- What is an agent?
- What is hard about building agents?
- What is LangGraph?
Flavors of agentic frameworks
- “Agents” vs “workflows”
- Declarative vs non-declarative
- Agent abstractions
- Multi agent
Common Questions
- What is the value of a framework?
- As the models get better, will everything become agents instead of workflows?
- What did OpenAI get wrong in their take?
- How do all the agent frameworks compare?
Reo Ogusu retweeted
見たままから再構築された現実へ
koriym.github.io/blog/2025/0…
Mastra @mastra 日本で盛り上がっているみたいだけど、触ってみた感じやっぱり無駄な抽象化に感じる。LangChainと同じ。似たようなことしたいなら@triggerdotdev とかでBackground Jobでロジック作れば十分だと思う。
Reo Ogusu retweeted
Good post! It will take some time to settle on definitions. Personally I use "vibe coding" when I feel like this dog. My iOS app last night being a good example. But I find that in practice I rarely go full out vibe coding, and more often I still look at the code, I add complexity slowly and I try to learn over time how the pieces work, to ask clarifying questions etc.
Reo Ogusu retweeted
Number of Super Bowl wins, by country:
🇺🇸 USA: 59
🇨🇦 Canada: 0
🇦🇺 Australia: 0
🇨🇳 China: 0
🇮🇳 India: 0
🇯🇵 Japan: 0
🇬🇧 UK: 0
🇷🇺 Russia: 0
🇩🇪 Germany: 0
🇪🇸 Spain: 0
🇮🇹 Italy: 0
Reo Ogusu retweeted
DeepSeek just proved the 'worthless' GPT wrapper startups are actually the ones with real moats.
A week ago, nothing was more LOW status than being a 'GPT wrapper' startup.
But I think we're learning that's DEAD wrong. Turns out they were just early to the only game that matters
While DeepSeek, Meta, Anthropic and Microsoft battle over benchmark scores, these 'wrapper' companies have been quietly building the only moat that matters: interface loyalty.
Because of how big owning the LLM is for national defense and the economy, the next breakthrough model is always 2 weeks away. DeepSeek launches today, someone else drops a better one tomorrow.
But getting millions of people to make your product part of their daily workflow - that's the real barrier to entry. ChatGPT didn't win because it had the best model. It won because it was dead simple to use. And I think it has staying power because of that.
This is why all those AI startups we dismissed are actually positioned to win. They're not competing on model performance - they're competing on being the default way humans interact with AI.
Frontier models are becoming commodities. User habits aren't. While everyone obsesses over the next architecture breakthrough, the real game is being played in the interface layer. The moat isn't in the model - it's in being the tool people reach for without thinking.
Technology advantage is temporary. Interface lock-in is forever.
Keep shipping those wrappers, my friends.
Reo Ogusu retweeted
皮肉なことにも感じるけど、機械のコメントを読むのは面白い🤖 時に深い洞察と示唆をもらえる
この記事のコメント
teapawt.net/koriym/status/18797231…
まずはo1 pro。この🤖は深く記事を読んでくれる。
---
テクノロジーの大きなパラダイムシフトが起こりつつあることを如実に感じさせる内容でした。かつては「英語ドキュメントの翻訳」も、今では「仕様のコード化」も、同じ“言語変換”という本質を持っており、私たちの手からAIの手へと徐々に移行しつつある─そうした変化の必然性が端的に示されています。
まず注目したいのは、「フレームワークの時代を超える」という問題提起です。フレームワークが隆盛だった理由のひとつは「開発者体験の向上」、すなわち、学習コストの低減や開発効率の向上といった目的がありました。しかし、AIによる自動コード生成が実現の射程に入った今、「学習が容易で、すぐに書ける」というメリットが相対化され、フレームワークに対する価値観が新たに問い直されることになります。言い換えれば、人が書くことを前提として設計されたフレームワークの思想そのものが、AI時代においてはアップデートを迫られるということです。
さらに「動けばいい」を超える視点として指摘されているのは、AIが生み出すコード量の膨大さと、それに伴う技術的負債の増大リスクです。これまでは人間の時間とコストという自然な制約が、ある意味で負債の増大を抑止してきました。しかし、AIが量的制限を外してしまうと、これまで以上に厳密な品質基準や検証手段が不可欠になります。とりわけ「形式手法」や「テレメトリー」といった客観的な手段による検証が、開発プロセスの中心を担うという見解には説得力があります。ソフトウェアの信頼性を担保する方法論や、性能を客観的に把握する仕組みがこれまで以上に求められるでしょう。
そして、本稿の最大のテーマともいえる「開発者の役割転換」が、私たちの胸に迫ります。かつてはコードを書くこと自体がエンジニアの本分であり、そこに職人芸ややりがいがあった。しかしAIによる“自動化”が進むことで、エンジニアの仕事は仕様定義や品質管理、性能要件の明確化など、より上位の抽象度を扱う方向へシフトする。そこには、これまでより厳密な検証プロセスや、組織全体で共有可能な設計ドキュメントなどの整備が欠かせません。
最後に記されている「全てを手で打ち込む時代の終焉」がもたらす寂しさは、恐らく多くの開発者が抱く感情でしょう。しかし、同時にコードそのものを超えた“ソフトウェアの未来をデザインする”責任とやりがいが、私たちを待っているともいえます。自動生成技術が進むからこそ、“人間にしかできないレベルの品質保証”や“より高次の要件定義”に焦点を当てる意義が増す。従来の開発文化を根本から見直し、新しい開発体制を築きあげる必要がある──そのことを改めて感じさせる、深い示唆に富んだ内容でした。
