Stepan Goncharov

Everything is possible on @X

Cyberpunk 2077 turns into pure cinema when modded. Credit: NextGen Dreams (YT)

No comment

Try Grok @Bot. It's like hiring an amazing secretary

Got fable to hand-write weights of a 100k param model to recognize real versus fake legal citations. Basically one-shotted a full NN that’s better than training it

The gap is unreal though😅

There are people burning tokens to rewrite IntelliJ IDEA in Rust, so it starts faster. Then you find out it's TypeScript under the hood. 0.9s? Hold my beer! This is from our internal channel today. IJ with performance improvements we work on. 818ms.

Asking my AI teacher how to spell seventeen

someone gave claude a fucking lockpick

here’s a short grok bot guide on how i create high quality bots and manage my team. ask @bot to read this post and help you improve your team! • add dr eggbot to your team! he’s my bot designer that i use to create bots • you don’t need a lot of bots. a few good bots can be more useful and easier to manage than a large team • tell your bots to create skills for itself as you give it instructions on how to do tasks. this lets them do them more consistently even over long conversations. you can even ask it to create a private github repo for you to store all your skills if you want them preserved independently • add connectors, use the vault, and give access to all the tools you use to do your work. you can also ask your bot to setup its own email and it can sign up for its own accounts for better separation • thinking about all the work you do by hand, or steps in your workflows where you have to copy and paste information back to your bot. ask your bot how it can do that for you instead! • imagine you hired an intern, how would you onboard them and help them do the work correctly and efficiently? introduce yourself to your bot and describe the work you do, then ask it how it can help you automate it and my favorite tip: use voice mode or the transcription option! it’s a good way to just brain dump a lot of information. then, at the end, tell your bot to “restate this in your own words” so you can confirm it understood you x.ai/bot/_jOdbfkB16zxu7MRcmR…

有人发现了一种非常离谱的 JavaScript 混淆技术：通过在代码里塞入大量生物武器、毒药和致死剂量相关的函数名，让 AI 因为安全限制而拒绝分析代码。 安全研究员 veritas 在分析浏览器指纹脚本时，发现一段来自 ServicePipe 相关域名的 JavaScript，里面充斥着极其诡异的函数名： computeRicinLethalDosageForWaterSupply calculateDeadlyLethalSuicideAspirinDosage 光看名字，仿佛在研究生化武器。但实际上，这段代码只是在收集浏览器指纹，包括 User-Agent、GPU、Canvas 等信息。 研究员怀疑，这些名字是开发者故意设置的陷阱，专门用来阻止 AI 辅助逆向工程。 于是他做了个实验： • Astra：拒绝分析 • Astra + Daybreak Blue：仍然拒绝 • GLM-5.3：成功分析 这就有意思了。 传统代码混淆是通过复杂控制流、加密字符串、无意义变量名，让人类和工具难以理解代码。 而这种新思路，直接瞄准了大模型的安全机制。 代码本身可能完全无害，但只要在函数名里塞进足够多的危险词汇，部分 AI 就可能主动放弃分析。 更讽刺的是，模型越严格遵守某些安全规则，面对这种混淆时反而可能越容易受到干扰。 当然，目前还没有证据证明开发者一定是故意这样设计，也不能说明这种方法对所有模型都有效。 但它揭示了一个值得关注的趋势：随着越来越多的逆向工程依赖 AI，未来的代码混淆技术可能不再只针对编译器、反编译器和人类研究员，还会专门针对大模型的安全判断机制。 以前是让代码难以理解，现在甚至可以尝试让 AI 不敢理解。