Ex_Files_NotebookLM_for_Research.zip
28.4 MB
Please open Telegram to view this post
VIEW IN TELEGRAM
Chat GPT can help you with a lot of ideas and you can implement it any way you like, there are endless possibilities.
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
❤11👍3
Claude can now learn directly from screen recordings
🔄 With the new "Record a Skill" mode, you simply record yourself performing a task while briefly explaining your actions. Claude will generate a step-by-step instruction set and repeat the process on its own.
Think of it as training an automated assistant in real time — show it what to do once, and it handles the execution for you.
🔨 The feature is already available for Pro, Max, and Team subscribers.
Think of it as training an automated assistant in real time — show it what to do once, and it handles the execution for you.
Please open Telegram to view this post
VIEW IN TELEGRAM
❤8
Graphic vector illustration portrait of a young [man/women] looking up thoughtfully, messy textured hair, wearing large black over-ear studio headphones and a vibrant red hoodie. Low-angle close-up shot, stylized comic book graphic novel aesthetic, detailed pencil draft lines, bold watercolor paint splatters in turquoise and crimson red on an off-white cream background, high contrast, artistic poster design, sharp lines, highly detailed.
Negative Prompt:
3d render, photo-realistic, photo, photography, real human skin texture, extra limbs, bad anatomy, ugly, distorted eyes, blurry, low resolution, over-saturated, deformed face, extra headphones, noisy background, text, watermark, signature.
Recommended Parameters:
- Aspect Ratio: 3:4
- Style: Graphic Illustration / Comic Poster Art / Vector Painting
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
❤12👍5🔥4
This media is not supported in your browser
VIEW IN TELEGRAM
❓ Tired of LLMs that hallucinate on complex tasks?
What if your AI could:
• Explore multiple step-by-step reasoning paths?
• Use automated verification to reinforce correct answers?
• Check its own work and self-correct?
• Autonomously decide when to call external tools?
GigaChat 3.5 Reasoning does all of this.
This open-source LLM (built on GigaChat 3.5 Ultra) actually thinks before answering. It uses proprietary linear attention for efficient long-context
handling, consuming 37% fewer tokens than DeepSeek V4 Flash Preview on math problems.
Real-world performance:
✓ IFBench: 44 → 77
✓ Natural Plan: 64 → 80
✓ LiveCodeBench v6: 56 → 85
🔗 MIT License. Weights on Hugging Face: fp8 | bf16
What if your AI could:
• Explore multiple step-by-step reasoning paths?
• Use automated verification to reinforce correct answers?
• Check its own work and self-correct?
• Autonomously decide when to call external tools?
GigaChat 3.5 Reasoning does all of this.
This open-source LLM (built on GigaChat 3.5 Ultra) actually thinks before answering. It uses proprietary linear attention for efficient long-context
handling, consuming 37% fewer tokens than DeepSeek V4 Flash Preview on math problems.
Real-world performance:
✓ IFBench: 44 → 77
✓ Natural Plan: 64 → 80
✓ LiveCodeBench v6: 56 → 85
🔗 MIT License. Weights on Hugging Face: fp8 | bf16
❤4