Karpenter: The Better Autoscaling Solution for Kubernetes

https://dev.to/aws-builders/karpenter-the-better-autoscaling-solution-for-kubernetes-part-1-4pd5

I love this!

یه موضوع جدیدی که این روزا خیلی مطرحه بحث مهندسی پرامپت برای این مدل‌های هوش مصنوعیه؛ یعنی اینکه چجوری و با چه ساختاری بهش ورودی بدیم که بتونیم خروجی بهتری ازش بگیریم. راجع بهش کلی کار شده، از مقاله گرفته تا راهنما و اینا.
این یه لیست خوبی از چیزای به درد بخور در زمینه‌ی prompt engineering عه:

https://github.com/dair-ai/Prompt-Engineering-Guide

https://learnprompting.org/

Generative AI Landscape

این هم نمودار خوبی از استارتاپ‌ها و شرکت‌هایی توی این حوزه است

Are you tired of Googling basic terminal commands every time you forget the syntax? Look no further! terminal-copilot is here to help.

With terminal-copilot, you can quickly and easily access commonly used terminal commands right from the command line. Simply type copilot followed by your desired command in natural language and let terminal-copilot do the rest.

For example, if you want to find a file ending in .txt, simply type: copilot find a file ending in .txt terminal-copilot will then display the correct syntax for the command you need: find . -name "*.txt" With options to execute, copy, or explain the proposed terminal command.

https://github.com/Methexis-Inc/terminal-copilot

And this seems lovely as well:
https://glasp.co/home

BREAKING: Microsoft CTO announces: GPT-4 is coming next week!
The model will be multimodal, including video features.

https://www.heise.de/news/GPT-4-is-coming-next-week-and-it-will-be-multimodal-says-Microsoft-Germany-7540972.html

این اگه جوری که فکر می‌کنیم و گفتند باشه، همه‌ی ترسایی که ملت از چت جی پی تی دارن مسخره است! چونکه that's the real danger!

میمش رو هم درست کردم براتون

اینم دیروز ریلیز شده و سر و صدا کرده:

This AI tool automatically animates, lights, and composes CG characters into live-action scenes.

https://twitter.com/rowancheung/status/1633922250742087687?t=le1Pa4YD_hGoV8wuUhntxQ&s=35

بابا دو دقیقه آروم بگیرید ببینیم چی کار داریم می‌کنیم آخه!
میری دستشویی میای یه چیز جدید هست 🚶🤦‍♂

بازم میم درست کردم براتون :)))

مایکروسافت در اقدامی مصور سازی ChatGPT رو جهت صحبت کردن و ترسیم و ویرایش عکس و متن منتشر کرد

paper: arxiv.org/abs/2303.04671

https://github.com/microsoft/visual-chatgpt

#مقاله

❇️ @AI_Python

پیش‌بینی راجع به امکانات (توییت):

*If* GPT-4 is multimodal, we can predict with reasonable confidence what GPT-4 *might* be capable of, given Microsoft’s prior work Kosmos-1:

- Visual IQ test: yes, the ones that humans take!
- OCR-free reading comprehension: input a screenshot, scanned document, street sign, or any pixels that contain text. Reason about the contents directly without explicit OCR. This is extremely useful to unlock AI-powered apps on multimedia web pages, or “text in the wild” from real world cams.
- Multimodal chat: have a conversation about a picture. You can even provide “follow-up” images in the middle.
- Broad visual understanding abilities, like captioning, visual question answering, object detection, scene layout, common sense reasoning, etc.
- Audio & speech recognition (??): wasn’t mentioned in Kosmos-1 paper, but Whisper is already an OpenAI API and should be fairly easy to integrate.

Note: the predictions are based on what Andreas Braun, Microsoft Germany CTO, allegedly said. They may or may not be accurate (that’s why I call it “prediction”). But Kosmos-1 is very real and rock solid. It offers a glimpse of either GPT-4 or whatever AI service that Microsoft will provide next. I find it difficult to believe Kosmos-1 will stay in the lab and not become a product.

In any case, prepare yourself for multimodal APIs - they’ll happen sooner or later!

مدل Kosmos-1 هم همونه که توی این مقاله هه یکی دو هفته پیش منتشر شد

Sometimes just being alive is success