Alibaba’s Qwen3.7-max appears to interpret response_format=json_schema differently than 3.6.
It now wraps a string-typed visible_reply field inside a message-list structure (which 3.6 didn’t do).
Either:
• the schema implementation has a bug on the new model, or
• 3.7-max changed the semantics of response_format
Has anyone else run into this?
#Qwen #Qwen3 #LLM #JSONSchema
Images generated w/ @OpenAI 4o looks all the same now 😩
Left 4o / right DALL E
After reinstall @cursor_ai due to some issues with the project rule "add new rule" button, now back to 045.17 instead of 046.5 and no updates available for universal and arm64 🥺😱😠. Before reinstall i was at 046.5!!! Can you help @cursor_ai ?
What`s about this?
Project-based startup company as learning/intern/experience center to try out, for pains and gains but with successful results!
Pps are working on projects given by other companies.
With mentorship.
@ideo has the pbl approach?!
Any thoughts?
🗓️ 10/23/24 🗓️
🚀🎉 Today, MEDUSAJS @medusajs is launching 2.0 🎉🚀
Make ecommerce great again 📈
🍿🍾🎉
Introducing Gemini 1.0, our most capable and general AI model yet. Built natively to be multimodal, it’s the first step in our Gemini-era of models. Gemini is optimized in three sizes - Ultra, Pro, and Nano
Gemini Ultra’s performance exceeds current state-of-the-art results on 30 of the 32 widely-used academic benchmarks. With a score of 90.0%, Gemini Ultra is the first model to outperform human experts on MMLU.
blog.google/technology/ai/go…















