My dear front-end developers (and anyone who’s interested in the future of interfaces): I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept): Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow

Day 15/ Nevermind, we're still cooking... and reset. Enjoy.

Day 15/ We're cooked

> this Honestly, this. People are surprised that I drive my agents by hand, not some magical Rube Goldberg thing. lock in on two or three things; drive them by hand and engineer recursive outcomes.

When I was writing Unreal Engine 1, my time was divided as follows: - Around 30% went to seriously deep coding on hard problems: assembly language texture mappers, C++ BSP trees, data persistence, object oriented systems design, and networking. - Around 70% was just typing and refactoring large bodies of code needed for a complete engine feature set. This was not hard, and while I was doing it my mind was mostly on the deeper coding topics, thinking and planning for what's next. It didn't feel much different from vibe coding today, except that it was just me typing code on an IBM Model M keyboard rather than prompting it and reviewing the results. So, it has always seemed perfectly logical that we would rely on AI for that 70%, once the AI could do it with a similar quality standard as we could, which has never been perfection. It came as no surprise that, after a few years of AI model evolution, it was able to take the reigns on that 70% and free up programmers' time for more valuable tasks. What's more of a surprise is the emergence of AI as a sort of insta-Carmack able to solve hard technical problems quite cleverly and often cleanly, and that it's able to reason about and work in complex 3D scenes both by operating the tools and by directly understanding the raw data files. I abandoned assembly language in 1998 when out-of-order CPUs made much simpler C/C++ code faster, and never I missed it. If prompting through architectural documents, concept art, and design plans can transcend typing code and tweaking vertices, that will enable developers to spend their time on higher-level, higher value technical and creative tasks. What matters is the end product, whether it's a game or an engine. Anything developers can do to try out more ideas and make better software and games faster is a win for everyone.

Argon has this amazing natural understanding of the world. It can do so many things from first principles. Here's a pelican riding a bike, using fourier epicycles. Video made by Argon. Time-synced Lyria 3.5 music prompted by Argon.

Claude Code × Blender MCPで「深夜のコインランドリー」の３Dシーンの作成していきます。 大雨の夜、1台だけ回る乾燥機と、チカチカする蛍光灯。 モデリングも質感もアニメーションも、ほぼ日本語で指示しただけです。 手順をまとめます🧵

i’m a little torn because i love how ruthlessly openai pivoted to ensure they had frontier pretraining and i do feel like dots is the right interface and i kinda love openai BUT anthropic always seems one step ahead. they’re not over active on x, they don’t have stores or images or dots. they just have world class models at coding and knowledge work. and taste doesn’t seem to me to be something easy to just hill climb. basically opus 5.5 is oneshotting some high level white collar work that astra spins its wheel on. i have way less dead tokens with opus because it has taste and genuinely understands. and if they’re somehow able to compete on price, it could be. dare i say it. so over.

I've found NB 2.1 follows instructions more closely and is really good with text.

Over the next 28 days, each day we’ll either ship one thing that is a clear improvement and relevant for most codex/work users or ship a full reset. Let the improvements begin.

I was spending 2000$ a month on codex plans 10 200$ subscriptions and now thanks to Opus 5.5 all I need is one 200$ Anthropic plan

Web crawlers /[•]\ #js x #css