some of the smaller models should work on a 14
COMPUTING
-
iOS Hardware Limitations for FP16 Model Execution
By
–
this is at q4, don't think it could run fp16 due to iOS limits
-
Computer Scientist Goals 2026: Skills and Achievements
By
–
What are your goals as a computer scientist this year?
-
Software Architecture Matters More as AI Adoption Accelerates
By
–
There will probably be more conventional software written in the coming decade than ever before; the architecture of that software still matters! Better and worse affordances for AI should make a difference.
-
Low Resolution Screens Larger Than Gameboy Pixels
By
–
oh you mean on the screens that have fewer pixels than a gameboy but are somehow still larger?
-
Database Design and Modeling with PostgreSQL and MySQL Guide
By
–
#Database Design and Modeling with PostgreSQL and MySQL: http://
amzn.to/4czh1cP v/ @PacktPublishing ——
#CDO #Analytics #DataScience #ML #AI #DataEngineering #SQL
——
Key Features:
Get to grips with fundamental-to-advanced database design and modeling concepts with PostgreSQL -
Ministral 8B Running Offline on Mobile at 10 Tokens/Second
By
–
Here’s Ministral 8B running at 10 tok/s on a phone.
— Aaron Ng (@localghost) 31 décembre 2024
Siri isn’t going to save you when you’re stuck without internet. An offline backup AI is essential. pic.twitter.com/nKmjb1Z5jGHere’s Ministral 8B running at 10 tok/s on a phone. Siri isn’t going to save you when you’re stuck without internet. An offline backup AI is essential.
-
VRAGE3 Engine Powers Space Engineers 2 Development
By
–
@janhlousek Our tech-director Cendo will be best to answer! I can say that SE2 is using the new generation of our engine – VRAGE3. Yes it is still C#/NET based, but has evolved since the XNA roots (actually even SE1 didn't have the XNA stuff anymore) IMHO, XNA was good, I liked
-
Cursor’s 5k tokens per second speed
By
–
Cursor now can "apply" with 5k tokens per second 🤯
— 🚨 AI News | TestingCatalog (@testingcatalog) 31 décembre 2024
How soon will we be getting isomorphic code that changes as you speak? 👀
h/t @cursor_ai pic.twitter.com/QNhyJpO5EkCursor now can "apply" with 5k tokens per second How soon will we be getting isomorphic code that changes as you speak? h/t @cursor_ai
-
Axelera AI Celebrates 2025 with Clean Code and Innovation
By
–
🎉 New Year, New Code 🤖✨
— Axelera AI (@AxeleraAI) 31 décembre 2024
As we ring in 2025, let’s toast to clean data, low latency, and fewer off-by-one errors! 🏆
2024 brought growth, challenges, and innovation—here’s to building something even better in 2025. 🚀#HappyNewYear from all of us at Axelera AI! ✨ pic.twitter.com/FquxyG8i72New Year, New Code As we ring in 2025, let’s toast to clean data, low latency, and fewer off-by-one errors! 2024 brought growth, challenges, and innovation—here’s to building something even better in 2025. #HappyNewYear from all of us at Axelera AI!