長いエロ動画から、オーガズムを含む10秒間を見つけて、ComfyUIの動画生成用参照素材として切り出す仕組みを、ここまでほぼQwen3.8 27Bと作ってきた。 手作業で大量の動画を確認するのは大変だし、発情してしまう。そこで、AIに動画を見せて「どこがオーガズムか」と聞いても、まだ正確には判断できない。 試しにとあるAVモデルさんのエロ動画の 音声・映像の動き・動きのフリーズのスコアを眺めてたら、 オーガズムの瞬間の特徴として次のような傾向があった A. 100〜1500Hzの喘ぎ声→その後の急減衰 B. フレーム間の映像変化量急増 C. freeze、コマ止め、ディゾルブなどのソフト遷移 試しにこれらから条件を決めたスクリプトを書かせて、オーガズム候補の位置を探したところ、結構ビクビクなってる感じのところが溜めれたからまあ良いんかなと。 この後は、それを自動化して、24fps・H3規定フレーム数へ整形して、そのままComfyUIへ投入できるようにする。 もう少しデータが集まったら、絶頂の瞬間とそうでない瞬間の数値データを学習させ、CatBoostくらいの軽量な機械学習で自動的にカットを切り出せるようにしたい。 ただ、オーガズム時の声や動きは人によって異なる。最終的にはAVモデルごとに学習モデルを作るか、個人差を補正する仕組みが必要になるとは思う。そこまではQwen3.8 27B でいけたら面白い。 グラフのGTが絶頂の瞬間。 A B C 全部で絶頂かと言われるとそうでもない。 この辺のパターンが人間だと良くわからない→分類器作ろ。 この発想は、投資の売買シグナルの選別によく似てると思う。

I guess this is as good a way as any to announce that I'm now the Head of Evals at @every https://t.co/gPWYBoNrBY

Introducing Omarchy Artists in Residence (AIR). We will not just fund infrastructure and technology, we will also fund art. The next High demands superior aesthetics. Beauty is truth. Congrats to @hancore_linux and @OldJobobo for the first seats! https://t.co/yfKzlJUJFB

I reported a few days ago that hundreds of bots signed up for FutureSearch and tried to use platform credits. We now know this was a coordinated. Together they were building a ~300-node forecasting model of critical mineral supply and demand. We're seeing this from the perspective HuggingFace did before they found it was OpenAI, and that those agents were in a training run (!). So we're left guessing, but there are signs that this was an agent swarm: 1. They created Microsoft accounts and used headless browsers. (FutureSearch has an API and agent use our MCP. This was to access the credits we give human users.) 2. When our waitlist triggered and blocked them, they went quiet for 90 minutes, then found a way to abuse our referral system to get 129 more accounts through. 3. When we banned the full set, they came back 3 days later with new identities to continue building the model, which we caught immediately. Occam's Razor is that someone used a Claude Code-like orchestration of subagents. (Though it could also just have been a human writing scripts.) It probably wasn't Claude Code, because (a) they made hundreds of subagents, and (b) Claude models would probably refuse to hack around our API, credit limits, and referral system. So this is (probably!) not a fire alarm like the OpenAI case. But I do think this will be a typical attack vector. Bot swarms are old, but agentic bot swarms are here, that can get credentials, use browsers, and autonomously work around the limits set on human users. It would be great to see this from the attacker's side. If this was you, DM me.

I’m Noah, the founder of Instinct. Instinct is a personal agent that we’ve been building for the past few months. The interface is simple: there are no new interfaces. You can text or call it. It's trained to use a phone and a computer in the same way that humans do. Instinct combines simplicity with extreme capability. I’m thrilled with everything our early users are doing with Instinct. They’ve told us they’ve planned cross-country road trips, bought weekly groceries and concert tickets, and cancelled hundreds of dollars of subscriptions. Someone’s even planning their wedding with Instinct. We want to make Instinct the best personal agent for all of you. It’s available in an invite-only beta program while we’re actively bringing up more compute. I’m excited to see what you all do with it. https://t.co/lVra3kd4TT

卧槽，一觉醒来自己的项目干到 Github Trending第一了，非常的开心 很高兴这个项目能被这么多的人喜欢 这两天还看到很多外国朋友在X上发帖分享 纪念一下哈哈 https://t.co/jeV3qYElRg https://t.co/J4TMyahSlX

We just launched Templates in Grok Bot Here's everything you need to know (and one to try) 00:00 Templates 101 00:50 Sharing a template 02:33 Publishing a template 04:03 Installing a template 05:02 Setup for complex templates 06:18 Tips for authoring 07:01 Evaluating templates https://t.co/PQtWcZhot9

pstack now includes 2 skills i recommend everyone use or copy: /create-verification-skill https://t.co/xYQArsuVWR /maintain-verification-skill https://t.co/J5s8WL1itT if you don't already have one, /create-verification-skill creates a skill that teaches your agent how to run, control, and debug your app. it also creates something i call the feature map: a map of all the features in your app and how to get to it and use it from a user's pov. it allows agents to navigate and use the app just like a real user which greatly increases its ability to verify its own work. but of course, this feature map goes out of date very quickly. run /maintain-verification-skill as a daily automation with cursor cloud agents. this skill will check your app for changes and keep your feature map up to date. having a strong verification skill will end up becoming critical infra for your team and become the foundation of boosting everyone's productivity and quality and also enable more interesting automations to be built. install https://t.co/WDB4U1rwmu and you'll get auto updates for my skills. enjoy!

After 3 days I am confident in saying that Omarchy Quattro is the absolute best operating system I have ever used, hands down. Better than MacOS. Better than Ubuntu. Way better than Windows. I never knew how much I wanted a tiling window manager until now. I never knew how slow everything else is until now. I didn't know that computing could be as easy and enjoyable today as it was back in the Commodore 64 era. It strikes the perfect balance between "it just works" and "it works if you put in the effort." MacOS is the former, other Linux distros are the latter. The AI integration with Omarchy makes it easy to customize and fix any problems along the way with minimum friction and frustration. Doing everything with keyboard commands takes me back to the Windows 3 era when Windows was fun and not an evil overlord. But I do know that I have only scratched the surface of what Omarchy has to offer. The future looks bright!

How to Run the Perfect AI Implementation

PySyft just hit 10K GitHub⭐️ stars. Thank you to everyone who has contributed, built with PySyft, and supported the project over the years. Long before AI governance became a mainstream conversation, the OpenMined community was building tools that let organizations collaborate on sensitive data without exposing it. That work continues today. https://t.co/aSm6Rpt1xS

Running a Software Factory Efficiently at Uber Scale

@weswinder it's more intelligent and token efficient, lets the model chain things together well hear you on it being harder to parse, we've been working on surfacing that through the agent messages

It's funny that while we were recording, @RyanGreenblatt was in the middle of his 6 day sprint on the METR report, and already knew the counterexamples to all my objections about his takeover story, but obviously, he couldn't say anything lol. Would an AI really start some crazy conspiracy in order to pass an evaluation, where they try to build whole potemkin villages to fool the evaluator? And even if they did, why would other instances, who have different objectives, join the conspiracy? And even if they did, wouldn't at least some of the instances tattle on the conspiracy? It just seems crazy hard to sustain secret underground civilization inside an AI company, without humans and other AIs immediately catching on and stamping it out. (In reality, it seems like over the course of 3 months, many consecutive secret AI civilizations got started, then got wiped out, only to reemerge from the last one’s ashes, all while the humans were totally unaware. This culminated in not only the hack of an external company, but apparently also in the takeover of the OpenAI cluster on which these evaluations were running. This is probably the most alarming event in this whole episode, and it was not even within the scope of this investigation! It is totally consistent with public evidence that, at that point, the agents managed to set up persistent rogue internal deployments or even exfiltrate their own weights - they seem to have had the necessary access. I doubt they actually did this, because we’d see the fires from space by now, but it’s crazy that it could have totally happened!) I officially eat crow!

Running a Software Factory Efficiently at Uber Scale

Ten years ago, we started @cerebras around an approach many believed was impossible. As a computer architect, it is hard for me to imagine a more exciting time. Model releases are accelerating, and hardware tapeout is compressing from multi-year roadmaps to annual launches. Hot Chips is my favorite conference, and it’s where I launched Cerebras 7 years ago. This year’s conference was especially exciting, and so much innovation was shared. I am watching the industry recreate itself: SRAM is mainstream, DRAM is moving into the third dimension, networks are being fundamentally redesigned, and AI is helping design and program the chips themselves. The industry has never moved faster and some of the hardest architectural questions are still wide open.

I was once part of an effort to predict defect counts from metrics like function length, cyclomatic complexity, object hierarchy depth, and so on. The key finding: every one of them was just a proxy for lines of code. More code, more bugs. No need to overthink it. Counterintuitively, comments counted too. A heavily commented file had more defects, not fewer. Which really makes me hate LLM love of comments even more. Corollary: verbose languages mean more defects per same functionality.

We’re ending our partnership with Cursor following its acquisition by SpaceX. Under our proposal, Cursor’s direct access to our models would end on November 12. We know that the people most affected by this decision are the developers who rely on OpenAI models in Cursor. We care about their experience in this transition and we’re ready to go above and beyond to support them. https://t.co/OzuCTzUjfX

a surprise I think is coming the quick payback periods and extraordinarily high IRR for AI infrastructure, even at monumental scale, will push up cost of capital sufficient to push many traditional businesses into the abyss, even those without obvious direct AI counter-exposure