コーディング — 今週のランキング
過去7日間に「コーディング」カテゴリで最もエンゲージメントを獲得した投稿。
We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle". As one idea to generalize it, I was interested what Opus 5 would do if I gave it the first paragraph of the Lord of the Rings, a 1M token budget (~$10) and asked for three js render of it. Opus went off for ~2 hours and wrote 5500 lines of code that (procedurally) rendered the story. It's kind of janky but fun. But it's a bit mindboggling that the LLM has to place and orchestrate various polygon assets in (x,y,z) coordinates and write code that animates it all, and that it even does anything at all. I also like this kind of examples because no one in their right mind would ever spend the time to write something this custom but LLMs have all the stamina and patience in the world, so it's an example where we go from "no one would ever do this" to "sure, why not, it's ~free". There might be a lot more. But I'm excited about creating hyper custom worlds that you can imagine dropping players into, e.g. here to participate in the LoTR story as a spectator NPC, or one of the characters, or etc. Something like an ephemeral GTA of X on demand. Last thought is that the domain of worlds/games exposes a weakness in LLMs: they can't easily audit their work because they aren't able to efficiently and natively perceive videos or play games within them. Here, Opus 5 had to very slowly and painstakingly take screenshots at different points, and it messed up a few times and created a bunch of jank. An example of raw capability (multimodal, gameplay) that I think is still quite lacking.
That's why I say to every single person I meet You have to book a flight to China now, please visit some of its cities, and NOT Hong Kong or even Shenzhen No visit ACTUAL China, go to Shanghai, Hangzhou, Chongqing, Chengdu, Beijing, Xi'an Ask Chinese people on here before you visit if you can visit their offices, they'll take you out for dinner and show their immense hospitality You and the other 1.6 billion people of the West all have a blind spot and have to understand this country to go forward in the 21st century and the only way to do so is to actually go there and walk around there Be brave and change your flight for Tokyo to a flight to Shanghai! Japan is sick of you tourists anyway, while in China you'll be the only tourist in a 100km2 radius!
The West's biggest blindspot is repeatedly underestimating China's speed and capabilities
Crazy to think the entire West is literally leaning on one single guy to do things at the same level China does
Terafab Texas will be the largest and most valuable building on Earth by far. And it will be stunningly beautiful.
gpt-5.6-sol is so good at building iOS apps it's crazy. Give it a dedicated Mac with computer use and let it run the simulator. Quality you get out is nuts.
We built a self-driving & self-correcting shared semantic layer on top of our databases, conversations, and docs. Everything is queryable & joinable—regardless of source! So now anyone at Replit can ask questions that previously needed a team of data scientists weeks of work.
When an agent starts with shared context, more people can get reliable answers. When truth is shared, AI becomes infrastucture. Read about how our internal truth layer drives our teams at Replit: https://replit.com/blog/ai-adoption
I have over 40 Claude agents/subagents running right now and my Framework desktop is barely breaking a sweat. Machine is a beast but the real star is Linux. I am so tired of MacOS for dev 🙃
We’re making great progress on improving the writing quality and design taste of Grok. Still a lot more to do, but I’m encouraged by how quickly we’re iterating. Please let me know any feedback. Grok 4.6 soon!
if you have been following his excellent work, @shloked has been breaking down every frontier labs' harness engineering for the last few months. excited to publish his deepest dive into ChatGPT yet as our newest guest on @Latentspacepod!
🆕 Unpacking ChatGPT Work https://t.co/wccYg8wY9K ChatGPT Work, an extension of the @openai Codex harness to cloud and general knowledge work, launched on July 9 and crossed 10M users 3 weeks later. @shloked guests with an A+ reconstruction of how Memory, Proactivity, Scheduling, Browser Use, Plugins, Skills and Tools work in this new harness that is bringing a full agentic experience to the almost 1B weekly active users of ChatGPT!
> Google was too nervous to release it and DeepMind was blocked from shipping products that could disrupt Google. bookmark for the next vc that asks you "what if <incumbent> builds this?"
@_chenglou I was part of that team. Basically ChatGPT one year before it came out. Called LMChat and then another codename. Google was too nervous to release it and DeepMind was blocked from shipping products that could disrupt Google. I think about this a lot.
TanStack Charts has moved fast since 0.0.0 just 2 days ago: 🧩 Composable guides and layouts 🧮 Built-in transforms 🎯 Focus marks and animated states 💬 Pinnable, portaled tooltips 🌊 Sankey diagrams from ordinary marks 🪄 Smarter scale and key inference 🪶 A React compact-scale line is 16.48 KiB gzip, with tooltips and portals excluded until imported 🌐 One definition across nine frameworks, SVG, Canvas, and SSR Still pre-alpha, already capable of some seriously weird charts. https://t.co/mwB2sLKHas
Sandboxes are hard. With all the “AI escaping sandbox” it’s easy to think “wow AI so scary,” but most AI companies, and recent “sandbox providers” are making very basic mistakes. At Replit we’ve been running sandboxes since 2016 and targeted by every hacker and state actor under the sun. So we learned a thing or two. Main advice: Assume zero-days exist — because they do — and think in layers of protection in a zero-trust framework. More here: https://t.co/3XGY0a1p3P
Reply with a dataviz/chart for any of the following you've either built or seen: - The prettiest (regardless of accuracy or usefulness) - The smoothest(animation/interaction/etc) - The most complex - The most useful - Or whatever you want, just write it in
i somehow believe in all these at once - more people become builders (can build stuff) - more personal software exists - software engineering looks different but becomes an insanely popular job - saas is dead - we have years of saas and other companies making insane amount of money - the internet becomes only for agents and uniquely designed personal projects - software maintenance will just be agents in a loop (for builders) - no one knows or cares what’s ai generated - people brands matter more - given more time (from agents doing stuff) we just do more stuff with agents - more creative people emerge
早期アクセス体験レポート 【第1弾】Grok Bot は、自分のMacを触るComputer Useとはちょっと違う https://qiita.com/Kinopee/items/5603bbb951f6b06d486e
福岡初（！？）Claude Communityイベントを行います。 対象は一般の方！（もちろんエンジニアもウェルカム） みんな仕事でどうやって生産性上げてるの？ そんな話を一緒に話す会にしたいと思っています。 「僕こんなふうにAI使ったよ」4分ずつ話してくれる登壇者も募集！ 日時：9月6日（日）18時30分〜 場所：FGN（Fukuoka Growth Next） https://t.co/TYaGY8VcWz
codex build me this but for the yet-to-be-discovered ai founders walking about sf/nyc/ldn highlight the most likely $10b ones
Announcing the NYC AI Atlas! An open source 3D map of the top AI startups in New York City. http://nycaiatlas.com
Grok Bot を使い始めてから、ChatGPT、Claude を使う機会が減った。既存のワークフローも便利になるけど、エージェントが自分専用のコンピュータ環境を持っているのがユニークで、使いこなすととても便利。 モデルは謎で、Grok 4.6 ではと疑っているけど、公式なアナウンスがないと分からない。
At Cognition we’re building the independent agent lab. Doing that well means developing a thriving ecosystem for every company to accelerate their own business with Devin. Thrilled to welcome @artlevy, former chief business officer at Brex, to make it happen here.
I've spent the last decade getting deals done. I’m now going to do them at one of the most important AI companies in the game. I am joining @cognition as VP of Global Partnerships. Eight years at Brex taught me how to sprint at what I do best. Grateful to the team that bet on me. Cognition’s insane talent density and ambition made it the obvious next move. The dealmaking opportunity is real. Time to get back in the arena. 🚀
【イベント参加者登壇者募集】 もっとギュギュッとワイワイやりたい！ 仕事でAIどう使ってるかリアルな話をお互いにしたい！ 登壇者と会場が一体となって、質問したり討議したり。 平日の午後、少し規模小さめだけど、誰もが楽しめる会を渋谷で8月27日14時からやります！ https://luma.com/claude-yk4r
Paul has been a Federal Circuit clerk, a patent attorney, a bar association president, a board director, a magistrate judge, and the chief legal officer at Coinbase. Now he’ll help us level up all things legal & gov affairs at Cognition. Welcome Paul!
Devin just got new counsel. Today I’m joining @cognition as Chief Legal and Global Affairs Officer.