Top stories in tech today: – Sora copycats flood Apple’s App Store
– Amazon's prescription vending machines
– Tensor Robocars will come ‘Lyft-ready’ – MIT and Harvard design ‘natural killer’ cells – Quick hits on other tech news Read more: https://
tech.therundown.ai/p/sora-clones-
flood-app-store
…
GENERATIVE AI
-

Sora clones flood App Store amid major tech innovations
By
–
-
AI Evaluation Method Using Embeddings and Likert Ratings
By
–
And before anyone complains, "which another AI rates" is a bit of an oversimplification (character limits!): as explained in the diagram, the free text response from the AI acting like a consumer is converted into embeddings & compared to reference statements with Likert ratings
-

LLM-Based Customer Intent Prediction Achieves 90% Accuracy
By
–
This paper shows that you can predict actual purchase intent (90% accuracy) by asking an LLM to impersonate a customer with a demographic profile, giving it a product & having it give its impressions, which another AI rates. No fine-tuning or training & beats classic ML methods.
-

Week highlights: CellTransformer, Figure 03 robot, Base Power funding
By
–
Dan's last Dose.
Peace in the Middle East.
Nobel winner lives best life.
Allen Institute's CellTransformer maps brains.
Figure unveils 03 robot that can do home chores.
Base Power Company announces $1B Series C .
+David Lynch on meditation. What a week for the optimists. -
Jamba Reasoning 3B: Tiny Open-Source Model Excels at Reasoning Tasks
By
–
@VentureBeat spotlights Jamba Reasoning 3B, our tiny open-source model that outperforms others across reasoning benchmarks and runs securely on-device. Read the feature
-

AI Amplifies Human Effort: Engineering Efficiency Through Vision
By
–
“AI should not replace human effort, it should amplify it. When our engineers can take a photo of a junction box and instantly know it’s fine, they spend less time on routine checks and more time creating real value. It makes their work easier and their impact greater. The
-
Testing 32B Model Release Impressions and Performance Feedback
By
–
hmm i liked the 32B variety that was released earlier need to test myself and see if its passes my vibe checks will report back on it later tonight
-

KAT-Dev-72B-Exp: Agentic Coding Model Ranks #2 SWE-Bench
By
–
HUGE a new Agentic coding model, fits on 4x RTX 3090s @ 4-bit, fully local KAT-Dev-72B-Exp by Kwaipilot – Claude Code setup guide included – ranks #2 on SWE-Bench Verified – excels at long-horizon coding + tool-use – multi-stage tuned: Mid-Training, SFT + RFT, Agentic RL
-

BAIR Researchers Win Outstanding Paper Award at COLM2025
By
–
Congratulations to BAIR Researchers from @trevordarrell lab whose paper "Hidden in plain sight: VLMs overlook their visual representations," was awarded an Outstanding Paper Award at #COLM2025 this week in Montreal, Canada. @xkungfu @tylerraye @databoydg
-
Unrealistic AI Hype and Follower Disappointment Cycles
By
–
Se sobre-emocionan ante la expectativa de algo que no tiene sentido, y luego se sobre-decepcionan cuando esas expectativas falsas no se cumplen. Y con ellos sus seguidores.