Vibe coding in AI Studio coming soon
@officiallogank
-
Gemini API Adds Custom Frame Rate Video Understanding Feature
By
–
Learn more in the Gemini API docs: https://
ai.google.dev/gemini-api/doc
s/video-understanding#custom-frame-rate
… Or paste a youtube link into http://
ai.studio and click the gear icon in the bottom left of the video! Great work by @AniBaddepudi and the team to ship this. -
Gemini API Now Supports Dynamic Video FPS Customization
By
–
We just shipped video FPS support in the Gemini API, so you can dynamically customize how many frames per second you want the model to see, unlocking lots of interesting new video use cases!
-
AI Studio announcement coming tomorrow with stakeholders
By
–
Talking about it tomorrow with folks, will follow up, for now AI Studio only
-
Improving Long Context Capabilities for AI Models
By
–
Focused on making long context better then extending to 2M again
-
Thinking Efficiency Without Increasing Total Capacity Budget
By
–
Even with the same thinking budgets? We did make thinking more efficient but total capacity to think is the same
-
Claude 2.5 Pro thinking feature minimum token limit details
By
–
Yes, the only model you can’t turn thinking off on rn is 2.5 pro, which goes down to 128 tokens, will be zero in the future revs if the model, but for now that’s the min.
-
Stable AI Model Reliability: Preview Changes, Stable Remains
By
–
Preview might change or go away, like it did with 03-25, but Stable is stable and not going anywhere.
