TechMD
@TechMDAI
🔬 MD fueled by a deep passion for Medicine & Tech. 🌐 Exploring the frontiers of VR/AR/MR & BCI. 🤖 AI enthusiast.
You might like
How Droid Handles 7M Tokens In One Session. Live interview in 5 mins with Luke Alvoeiro from Factory AI.
Honestly, since getting Vision Pro I haven’t used the Meta quest 3. I feel a lot of guilt. #VR
Really cool!
Deep Agents repo is without a doubt the best resource to understand the next generation SOTA agents architecture. The @LangChainAI team has done an amazing job simplifying the concepts behind those agents capable of long horizon tasks. Knowing this repo is a must for every…
💻Deep Agents CLI Using the deepagents package, we built a simple coding CLI as an example of a coding application you could build on top of deepagents We added in a concept of memory so that it would remember instructions and guidance over time Blog: blog.langchain.com/introducing-de……
Gigawatt-scale Stargate data center is the largest single investment in Michigan history: wzzm13.com/article/news/l…
today I’m excited that you can now use @getstobo in beta with our TestFlight on Mac here’s a special Halloween teaser 👻 Stobo Studio allows you to make apps for Vision Pro, in minutes
All palaces are temporary palaces All theories are provisional theories
Andrej Karpathy says you should learn AI depthwise, not breadthwise. Most education is breadthwise: watch lectures, memorize formulas, and trust you'll need it later. Karpathy flips this by learning "depthwise, on demand." What this means: Pick a project, start building, and…
In a few hours, I’ll share a remarkable medical discovery by GPT-5 Pro. A physician friend serendipitously discovered a new treatment for an allergic disease. Independently, GPT-5 Pro identified the same therapy in one shot by repurposing available drugs! It’s a profound story!
I'm very weary of any product where the hype-to-ship ratio is high. In AI, in robotics, in microprocessors, really any category. Whenever I see a company which does hype related activities really well (great at social media, makes awesome launch videos, has an absurdly well…
Measuring with Muse on Apple Vision Pro – is it accurate?
Amazing job here! Calling 40 Agents in Parallel on M3 Ultra with 40 instances of gpt-oss-20b with LMStudio!
Mac Studio M3 Ultra's massive 512GB memory is perfect for parallel agent calling! Here I used @lmstudio to run *40* instances of @openai's gpt-oss-20b-mlx and got 35% performance boost compared to sequential API calling. @awnihannun, next I'll do it with batching like you said!
160 tok/s in full precision on a M3 Max 🔥
Deepseek OCR now on MLX :) Thanks for the patience! I finally found and fixed the bug on the LM part that was stopping it from understanding the Vision Tokens. New release later today, probably alongside batch infer to allow you to process N documents at once.
Gave another Apple Vision Pro demo last night. Went to do rideshare & ended up yapping about Teslas & Apple Vision Pros for 2 hours with a total stranger while supercharging . Apple Vision Pros & Bros 💪🏽😂
United States Trends
- 1. Jayden Daniels 21K posts
- 2. Dan Quinn 6,466 posts
- 3. Seahawks 35.8K posts
- 4. Sam Darnold 14.4K posts
- 5. Commanders 48.2K posts
- 6. Jake LaRavia 3,826 posts
- 7. #RaiseHail 8,513 posts
- 8. Bronny 12.6K posts
- 9. jungkook 593K posts
- 10. Joe Whitt 2,189 posts
- 11. Marcus Smart 2,966 posts
- 12. #RHOP 6,485 posts
- 13. Jovic 1,046 posts
- 14. Jaxson Hayes 2,784 posts
- 15. #BaddiesAfricaReunion 5,173 posts
- 16. 60 Minutes 65.9K posts
- 17. Ware 5,021 posts
- 18. Larson 20.1K posts
- 19. Lattimore 2,487 posts
- 20. Denny 19.4K posts
Something went wrong.
Something went wrong.