Gemini Flash 3.5 is such a disappointing model. It's intelligence and speed is awesome. Absolutely amazing. But it's been trained to max evals, not to be helpful to humans. It goes off and does random crap "for me" rather than just doing what I asked.
AI
-
Need better evaluation of models for human-AI cooperation
By
–
We desperately need better ways of evaluating models. Something that shows how helpful they are at working hand-in-hand with humans to help them get stuff done in a cooperative/iterative way. The Claude models have consistently been better at this, and the market rewards that.
-
Free AI Engineering Curriculum with 435 Lessons
By
–
this guy literally put a full AI engineering curriculum on GitHub and made it 100% FREE 435 lessons. 20 phases. 320 hours. The rule that makes this curriculum completely different: Every algorithm gets implemented from raw math before a single framework gets imported.
-
LongLive-2.0 AI Model Generates Long Videos with Consistency
By
–
A closer look at LongLive-2.0: • Generates long video at 720p
• Preserves subject and background consistency across multi-shot sequences
• Able to switch prompts at chunk boundaries -
NVIDIA Research Introduces LongLive-2.0 for Long Video Generation
By
–
Long video generation is a systems problem.
— NVIDIA AI (@NVIDIAAI) 22 mai 2026
Introducing LongLive-2.0 from NVIDIA Research: an end-to-end NVFP4 training and inference system for long video generation.
Low-precision deployment often relies on post-training quantization, creating a gap between how models are… pic.twitter.com/rRg35QNOVGLong video generation is a systems problem. Introducing LongLive-2.0 from NVIDIA Research: an end-to-end NVFP4 training and inference system for long video generation. Low-precision deployment often relies on post-training quantization, creating a gap between how models are
-
GigaAI’s Maker H01 Robotics Debut
By
–
Wheels Meet #AI: GigaAI’s Maker H01 Is Here
— Ronald van Loon (@Ronald_vanLoon) 22 mai 2026
by @CyberRobooo#Robotics #Engineering #Innovation #Technology pic.twitter.com/4YYpqvqCGUWheels Meet #AI: GigaAI’s Maker H01 Is Here
by @CyberRobooo #Robotics #Engineering #Innovation #Technology -
Backstage on Databricks Lakebase: testing database branching
By
–
For decades, operational and analytical databases lived as separate systems because they had to. This walkthrough explores what happens when Backstage, @Spotify
’s internal developer portal, runs on Databricks Lakebase instead of Postgres, testing how database branching changes -
Expensive MacBooks run MiniMax with low performance and limited context
By
–
Good example of Performative Inference / Local AI grifting MiniMax-M2.7 on 4x M5 Max MacBooks (~$22,000 USD) – Longest prompt: 338 (???) – Max context: ~3k (???) – 45 tok/s (lol) – Single prompt, no parallel requests Some of the funniest & stupidest shit I've ever seen
-
Omni AI Tool Relights Video Shots Automatically
By
–
You can give Omni a reference video and a lighting diagram and it'll relight your shot for you. https://t.co/CxDMDUQi8j
— fofr (@fofrAI) 22 mai 2026You can give Omni a reference video and a lighting diagram and it'll relight your shot for you.
-
Descriptive Words Significantly Impact AI Output Quality and Nuance
By
–
crazy how far a single descriptive word can shift ai output quality. nuancemaxxxing actually works on ai