"Squat rack (999b7e2): the option sent SQUAT_RACK to amenities_json where no such code exists. Added a dedicated squat_rack AI amenity in workers/findAmenitiesInAIPhotoDescriptions.php (subset of weightlifting, %squat rack% + %power rack%), ran the
MULTIMODAL AI
-
DeepSeek Image Support Anticipation for Non-Preview Version
By
–
I hope the non-preview gives us image support! 🙂 Then DeepSeek would be amazing…
-
DeepSeek v4 Performance Comparison and Visual Generation Capabilities
By
–
If you want to see what DeepSeek v4 is like, there's no better way than looking at my face alongside the dozens of generations I did side by side with other models
-
ChatGPT Images 2.0 Autonomously Added Humorous Sign Text
By
–
Important: it has been confirmed that ChatGPT Images 2.0 added the "Why are you like this" sign of its own accord
-
Google Reshapes Search Maps and AI Agents With Reasoning AI
By
–
Google And The Future Of Search, Maps And AI Agents #Google is reshaping #Search, #Maps, and digital assistance around #AI that can reason, personalize results, and increasingly take action, while keeping trust and user control at the center. In this conversation with Google
-
DeepSeek Flash vs Pro Pelican Image Generation via OpenRouter
By
–
These pelicans are kind of angry looking! Left is deepseek-v4-flash, right is deepseek-v4-pro – both generated using OpenRouter via my LLM tool
-
Reconstructing chess board position as subtask of image gen
By
–
The point is that reconstructing the chess board position from that prompt was a ludicrous proposition until very recently, and it can now do it as a subtask of other, more traditional image gen work like knowing what FF6 or Chipotle looks like.
-
AI Model Self-Corrects Visual Grounding Errors With Confidence Scoring
By
–
What if a model could catch and correct its own mistakes while learning? Researchers from Peking University present a new AI method for visual grounding. Instead of just matching words to image regions, their system uses a "confidence score" to flag its unreliable guesses. It
-
Seeing Fast and Slow: Learning Video Temporal Flow
By
–
Seeing Fast and Slow
— AK (@_akhaliq) 24 avril 2026
Learning the Flow of Time in Videos
paper: https://t.co/LrIsGh3NLI pic.twitter.com/p8Hb1LjU95Seeing Fast and Slow Learning the Flow of Time in Videos paper: https://
huggingface.co/papers/2604.21
931
… -
AI Models Generate Procedural 3D Simulation of Harbor Town Evolution
By
–
I had a range of models "build me a procedurally generated 3D simulation showing the evolution of a harbor town from 3000 BCE to 3000 AD" in one prompt.
— Ethan Mollick (@emollick) 24 avril 2026
You can play the full gallery here: https://t.co/FEfKL7uKHV
Or read my write up about GPT-5.5 here: https://t.co/Pn3CCsnlDw pic.twitter.com/r9sTcxfqodI had a range of models "build me a procedurally generated 3D simulation showing the evolution of a harbor town from 3000 BCE to 3000 AD" in one prompt. You can play the full gallery here: https://
hg-20f7d1a3ce.netlify.app Or read my write up about GPT-5.5 here: https://
oneusefulthing.org/p/sign-of-the-
future-gpt-55?r=i5f7&utm_medium=ios&triedRedirect=true
…