Glad to hear external validations like this for the Gemini #DeepThink IMO model we shipped last month π Stay tuned for future updates!
GENERATIVE AI
-
Planning with Reasoning using Vision Language World Model
By
–
Planning with Reasoning using Vision Language World Model pic.twitter.com/RZF8SVpV17
— AK (@_akhaliq) 4 septembre 2025Planning with Reasoning using Vision Language World Model
-
Extended conversation length feature improvement released
By
–
Awesome. It was much needed for longer chats.
-

EmbeddingGemma: Multilingual On-Device Embedding Model in Browser
By
–
model carrot vibe coding another Google EmbeddingGemma app, a sota multilingual embedding model perfect for on-device use cases using transformers.js and onnx-community/embeddinggemma-300m-ONNX At only 308M params, the model can run 100% locally in your browser app:
-

ChatGPT Now Lets Users Branch Conversations Explore Multiple Paths
By
–
By popular request: you can now branch conversations in ChatGPT, letting you more easily explore different directions without losing your original thread. Available now to logged-in users on web.
-

Liquid AI Japan 350M Model Rivals GPT-4o Translation Performance
By
–
Liquid AI Japan cooked with this 350M param model on par with GPT-4o for English Japanese translation That's a really nice example of fine-tuning done right
-

MCP Protocol Adoption and Product Terminology Evolution
By
–
Ah, as it turns out, we're calling them connectors too in our product. My gut feel is that as the protocol gets adopted and matures, we will gradually stop referring to it. For example, we don't say "http sites", we just call them "websites". MCP is kinda of technical term for
-
Compound now visits web pages for better answer grounding
By
–
Compound also now has the ability to visit specific web pages to get more content for better answer grounding… 2/3 pic.twitter.com/9cCnvYs1p4
— Groq Inc (@GroqInc) 4 septembre 2025Compound also now has the ability to visit specific web pages to get more content for better answer grounding… 2/3
-

Cerebras Qwen Coder vs Grok: throughput and pricing analysis
By
–
Grok fast vs. Cerebras fast
Grok Code Fast: 160 TPS, $1.5/M tokens
Cerebras Qwen Coder: 2,000 TPS, $2/M tokens
Cerebras: 13x faster, 33% higher cost, ~9x better price-
performance -

Hugging Face Releases Impressive New Work and Blog Post
By
–
Hugging Face did it again! Insane work, beautiful blog post.