Ivan Fioravanti ᯅ (@ivanfioravanti) on X (original) (raw)

GenAI/LLM addicted, Apple MLX, Cloud computing, Kubernetes, Technology Advisor, Investor and Co-Founder & Board Member of CoreView.

• 
  After finishing reading DeepSeek R1 paper, I must say humans must wake up and understand that a new way of living is on the horizon, in the past jobs were requiring strength an machines solved the problem, next wave required intelligence and machines are gonna solve this. We
• 
  o1-pro, I changed my mind, after 3 hours of deep discussion on context, plans, and strategy for 2025-2026, I believe it could excel as a Top Manager or even a C-Level. Conversation was challenging on both sides, with insights emerging from the synergy of human and AI reasoning 🤯
• 
  Tomorrow will be a big day for LLM models! And I'm not talking about Grok 4. I'm talking about Open Models for coding 🤐
• 
  Gemini 2.5 Pro available in Cursor! YES!!!!
  
• 
  Another incredible p5js animation created by the new King: Sonnet 3.7 Thinking! It's a kind of magic!
  
• 
  Qwen 3 0.6B is Ultra powerful if fine-tuned! Here I got 83.5% on classification tasks! Only Gemini 2.5 Pro does better with 85%! Video is in real time on M3 Ultra!
  
• 
  Hey
  @tim_cook
  if you see a spike in M2 Ultra and M3 Max sales in Q4, please look at your Apple Machine Learning Research team. They did the magic: MLX 🪄
• 
  🔥 o3-mini-high beats deepseek r1 and o1-pro! in a p5.js challenge! 03-mini result is so good that deserves a video on its own. deepseek r1 (bad result) and o1-pro (better) in comments below. Prompt in last comment. 1/4
  
• 
  Wait, what? This is much better than DeepSeek-OCR!
  
  Replying to @allen_ai
  On olmOCR-Bench, olmOCR 2 scores 82.4 points, up from 78.5 in our previous release—increasing performance across every document category. 📈
  
• 
  Apple Silicon users go install MFLUX now! - Fine tune you Flux LORA on fal.ai- Download them locally - Generate as many images as you want on your Mac thanks to
  @filipstrand
  and MLX! You can use your custom Lora both on schnell or devgithub.com/filipstrand/mf…
• 
  I'm sure many already knows: you can use DeepSeek V3 in Cursor right now: - add openrouter.ai/api/v1 as OpenAI Base URL - use deepseek/deepseek-chat as model - use it in chat (not in composer) Here the combo created a snake game eating AI companies. 3 turns needed to get it
  
• 
  This works on Mac too! Pinokio + Hunyuan Video + CivitAI John Wick LORA below and you are ready to go! 🔥🔥🔥 Video and LORA link below 👇
  
  
  
  Hunyuan vid2vid severance to John Wick Made by allhailthealgo Brilliant. One of the best I’ve seen
• 
  GenAI is a total complete game changer! You need to embrace it NOW! Tomorrow is too late! I am at least 3X productive now! No jokes! I am using: -
  @perplexity_ai
  for Search -
  @phindsearch
  for coding search, brainstorming, study -
  @cursor_ai
  to replace VSCode, copilot++ is
• 
  How long to transcribe 3 hours of video locally on macOS with mlx_whisper? - M2 Ultra 4:34 mins - M3 Max 4:56 mins Apple MLX: fast and easy!!! 🔥🔥🔥 pip install mlx_whisper