Here is an example: https://www.dailymail.co.uk/news/article-15476463/Trump-tell...

Do you normally run Opus by default? It seems the Max subscription should let you run Sonnet in an uninterrupted way, so it was surprising to read.

What are some standard benchmarks you look at in this space?

Do you think a more messier math benchmark (in terms of how it is defined) might be more difficult for these models to get?

This is a SendGrid alternative (transactional emails, potentially with a nice API).

OpenAI does not provide many details about their models these days but they do mention that the "Advanced voice" within ChatGPT operates on audio input directly:

> Advanced voice uses natively multimodal models, such as GPT-4o, which means that it directly “hears” and generates audio, providing for more natural, real-time conversations that pick up on non-verbal cues, such as the speed you’re talking, and can respond with emotion.

From https://help.openai.com/en/articles/8400625-voice-mode-faq

ra-aid works pretty well with Ollama (haven't tried it with Devstral yet though)

https://docs.ra-aid.ai/configuration/ollama/

One option would be https://geminicodes.co/ -- a CLI tool with Claude Code-like aesthetics.

It is a hobbyist weekend project though, the experience with Aider or ra-aid might be much better.

You can also try the HuggingFace Space at https://huggingface.co/spaces/Qwen/QwQ-32B-Demo (though it seems to be fully utilized at the moment)