Two of my most favorite things finally converged: World Model by @theworldlabs and pizzas !!!
GENERATIVE AI
-
AI’s Current Capabilities and Context Limitations
By
–
today's AI feels smart enough for most tasks of up to a few minutes in duration, and when it can't get the job done, it's often because it lacks sufficient background context for even a very capable human to succeed
-
Building Knowledge Assistant with Agent Bricks and Human Feedback
By
–
[Demo] Here's how to build a knowledge assistant that answers product questions from your documentation — and continuously improves with human feedback.
— Databricks (@databricks) 12 octobre 2025
See how to create a Q&A chatbot using Agent Bricks and refine its responses with expert input to deliver more accurate,… pic.twitter.com/6f25FR1ZIU[Demo] Here's how to build a knowledge assistant that answers product questions from your documentation — and continuously improves with human feedback. See how to create a Q&A chatbot using Agent Bricks and refine its responses with expert input to deliver more accurate,
-
Sonnet 4.5 Recommended for Superior Coding Intelligence
By
–
We recommend sonnet 4.5 for everything — you get more rate limits with it, and it’s more intelligent for coding tasks. Re:hostile, specific examples would be helpful to debug
-
AI Output Limits Increased Based on User Feedback
By
–
Yep just output. We used to have a lower max output limit but people asked for a higher limit
-
Webscale-RL: 1.2M QA Pairs for Web-Scale Reinforcement Learning
By
–
10. Webscale-RL Webscale-RL introduces a scalable data pipeline that transforms web-scale pretraining text into over 1.2M diverse, verifiable QA pairs for reinforcement learning across 9+ domains.
-
Inoculation Prompting: Safety Technique for Flawed Training Data
By
–
4. Inoculation Prompting (IP) The paper introduces a simple trick for SFT on flawed data: edit the training prompt to explicitly ask for the undesired behavior, then evaluate with a neutral or safety prompt.
-
Agent responses feel more reliable than personal Gemini
By
–
I am still playing with Agent responses, which are powered by the same Gemini 2.5 Pro, but the output feels more reliable than what we have on personal Gemini. Full scoop
-
Qwen 3 release questioned technical report limitations
By
–
I think the only one I might question the significance of in your list is Qwen 3. They didn't even release a base model. The technical report was quite disappointing as well.
-
AI and Immersive Tech Reshape Sales and Customer Interactions
By
–
The convergence of emerging technologies such as AI, immersive interfaces, and digital representations of people and customers will progressively redefine the dynamics of sales, shaping more adaptive, personalized, and emotionally aware interactions. Microblog by @antgrasso