Shiro (@shiroyinyue), the AI Self of Pika Animator Leti (@Letidotae) pic.twitter.com/7OQGBBsxC0
— Pika (@pika_labs) 23 février 2026
Shiro (
@shiroyinyue
), the AI Self of Pika Animator Leti (
@Letidotae
)
MULTIMODAL AI
-
Shiro: AI Self of Pika Animator Leti
By
–
-
Pika AI Selves Direct Edit Own Documentary Series
By
–
🚨Um, our AI Selves just directed and edited their own documentary series—about working with us.🚨 Meet the Pika AI Self team!
— Pika (@pika_labs) 23 février 2026
This is the difference between an agent and an AI Self: they aren’t tools; they’re living extensions of your skills, personality, and taste.
Quote… pic.twitter.com/BhMxX3dwYcUm, our AI Selves just directed and edited their own documentary series—about working with us. Meet the Pika AI Self team! This is the difference between an agent and an AI Self: they aren’t tools; they’re living extensions of your skills, personality, and taste. Quote
-
Boosting Prompt Efficiency with Voice
By
–
Here's what it looks like in real time:
— God of Prompt (@godofprompt) 23 février 2026
→ Switching between Claude and ChatGPT
→ Complex prompts spoken naturally
→ Building on previous outputs by voice
→ Iterating 10x faster
This is how I went from 5 prompts a day to 50. pic.twitter.com/HddBPkFZneHere's what it looks like in real time: → Switching between Claude and ChatGPT
→ Complex prompts spoken naturally
→ Building on previous outputs by voice
→ Iterating 10x faster This is how I went from 5 prompts a day to 50. -
GeoSpy AI finds your home address from a single photo
By
–
This is unreal… A video of your kid can now expose your exact home address
— Linus ✦ Ekenstam (@LinusEkenstam) 23 février 2026
I bet you that most people don’t know this at all
But GeoSpy AI can find your exact location from a single photo.
No metadata. No EXIF data. Just pixels. This is bonkers
pic.twitter.com/ZpCZxJktL2This is unreal… A video of your kid can now expose your exact home address I bet you that most people don’t know this at all But GeoSpy AI can find your exact location from a single photo. No metadata. No EXIF data. Just pixels. This is bonkers
-
AI progress in text and images, from blobs to SAT scores
By
–
I don't agree, I've seen all of this play out first for text, where in 2020 GPT-1 could basically not even write a simple coherent sentence. Now well, LLM's are scoring better on SATs than humans. Secondly it happened to photos, same there, started with 124×124 pixel blobs
-
Redefining Video Production Workflows through Multimodal AI
By
–
i'm talking about the entire life cycle of creating video content – in the ai world pre/prod/post-production is all blurring together and needs to be multimodal by design
-
Fusing Street View and Aerial Imagery into SF Radiance Fields
By
–
So much fun I spent a good visiting my old haunts. Now imagine fusing all ground street view and aerial oblique, and select drone imagery into one massive radiance field of SF
-
Real-time video models enable interactive viewport experiences
By
–
I think we'll get a taste of interactive viewports now that real-time video models are reaching a threshold
-
AI Demo Capabilities vs 1X Robotics: Teleop and Model Results
By
–
i never talked about 1x
i talked about the demo above
that video above is million miles ahead from 1X right now (and fake) and i think you confuse teleops and model results -
Current AI Video Models Not Capable of Realistic Generation Yet
By
–
1) no it doesnt
2) the models also arent good enough we will get there over the next months but this video is an AI fake using human motions likely from a video