We've developed a secure paste feature replacing traditional clipboard APIs. Users will be able to take away clipboard access from apps to use this instead. It integrates into the standard selection toolbar, input methods, accessibility services and keyboard shortcuts. We plan to get it merged soon. A small subset of apps including those written in Flutter implement their own text selection toolbar. We've worked around this by adding a Paste button to the default keyboard. We'll be replacing AO…
【Krea 2 Turboが爆速化！4ステップで高品質な画像を生成できるLoRAが登場】 Krea 2 Turboの新しいLoRAアダプタ「chk60K」が登場しました！なんと、従来の8ステップをたったの4ステップに削減しつつ、教師モデルと同等以上の細部エネルギーを実現しているそうです！✨ 推論速度は約1.6倍に高速化され、denoise処理にかかる時間も1.8倍速くなるとのこと。テクスチャの質も向上していてすごいですね！ 導入もすごく簡単で、diffusersやComfyUIにドロップインで使えるため、カスタムノードやコードの改修が一切不要です。guidance scaleを0.0に固定するだけで、そのまま利用できるのはありがたいですね！ プロンプト認識損失と対立損失が組み込まれており、テクスチャの保持力やプロンプトへの適合度も大幅にアップしています。クリエイターの方々はぜひチェックしてみてくださいね！🎨 #画像生成AI #StableDiffusion
【AI動画生成が爆速＆映画級に！？🎬✨】 「動画生成って時間がかかるし、パソコンが重くなる⋯」と悩んでいませんか？ 実は最新技術「MiniMax H3 Fused Turbo SLA」を使えば、たった4ステップで超綺麗な動画が作れちゃうんです！ 👇️ このスレッドで解説していきます！ #ComfyUI #MiniMax
AstraでSubagent利用するとUsage消費ペースが激しすぎる問題への対策
やっとAimeを物理カードからスマホに移行できた。スマホ一台でログインも決済もできる快適キャッシュレスオンゲキ環境を手に入れたが知らないとトラブルになる要素満点だから書いておこう。 #Aime
truck + C4 + tank = @WARDOGS #WARDOGS100k
これ覚えておくと良いよ。 https://x.com の前に adhをつけるとURLから本文が読めるようになる。 検索などをしたい場合はCodex等で fa0311/twitter_api_safe_relay を用いれば良い。
私にとって「かわいい」はずっと研究対象で、平面情報しかないキャラクターを立体化するときに、どのように「かわいい」を引き出せるか様々な方向から日々考えています。 レゴブロックで作る立体化は、解像度の粗さが見る人の補完を促したり、他素材にはない「かわいい」を引き出すポテンシャルあり。
The Skill Quietly Minting The First Solo Millionaires Of The AI Era
Hello, due to platform compliance requirements, currently uploading creatives (both image and video creatives) containing realistic human faces is not supported. To safeguard user rights and content safety, the system will automatically block such creatives, and video content cannot be generated after uploading. This means that if you upload photos of real people (especially those with clear and recognizable faces), the model will not be able to process the corresponding generation. We understa…
Spent 2 hours figuring out how to get past Seedance 2.0's real-person filter. Here's what actually works. 1️⃣ Feed multiple reference photos into Nano Banana Pro → generate a 9-grid portrait. This usually slips right through the filter. 2️⃣ Still rejected? Convert the 9-grid to line art in nano banana pro → describe the face in your prompt (features, hair, skin tone). Pass rate improves a lot. Basically you're just lowering the "real person" confidence score enough that the classifier lets it t…
Guys you aren’t going to believe this…
Cohencidence??
Wait for Grandma 🤯 if you are married, I advise you not to open the commentsss
Bro must have watched all the videos on porn hub. This ball knowledge is too much
How We Built a Next-Level Landing Page (and how you can too)
The door opens soon. If you’re on the list, you’ll know before anyone else. Join here: http://intheassembly.com
The Second Brain Is Not a Storage System. It's a Compiler.
How many 7s and 4s does it take before coincidence starts looking like a code? And even if you don’t believe in the numbers, they’re saying it openly: the world is being reshaped for a New Order. Watch my Series https://realityrevolt.com
If you aren't yet bold enough to install the Codex app, you can stay in the presence of your orange crab and point it at GPT 5.6 Sol. Takes 5 minutes. Kudos to Theo for explaining one of the ways to get this done.
Step 1: Install CLIProxyAPI
Step 2: Connect
Step 3: Define following alias and enjoy claudex
```
alias claudex='CLAUDE_CODE_SUBAGENT_MODEL=gpt-5.6-sol \
CLAUDE_CODE_ALWAYS_ENABLE_EFFORT=1 \
CLAUDE_CODE_MAX_TOOL_USE_CONCURRENCY=3 \
ENABLE_TOOL_SEARCH=false \
claude --model gpt-5.6-sol'
```
If this gets blocked, I owe you a reset.
Claude Design is insane.
❤️🔥Just recorded a 18-min tutorial on how to build animated, award-winning websites with Claude Design + Opus 4.7!
LEARN HOW TO CREATE PROFESSIONAL WEBSITES USING GEMINI 3.1 + SEEDANCE 2.0 IN JUST 15 MINUTES
20,000+ people have already joined the waitlist.
I’ll be closing access soon.
A few random notes from claude coding quite a bit last few weeks.
Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.
IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They wi…
