OK, here's a resolution - I managed to get it to think using these settings: 'thinking': { 'type': 'adaptive', 'display': 'summarized' }, 'o…

OK, here's a resolution - I managed to get it to think using these settings: "thinking": { "type": "adaptive", "display": "summarized" }, "output_config": { "effort": "max" } Without "display": "summarized" I couldn't tell if it thought or not https://x.com/simonw/status/2046740170003947854 @137ry https://gist.github.com/simonw/0f1a37092fd0814bae75050eced48889 seemed to work - the problem is it no longer reports "reasoning" tokens as a separate line item from output tokens so I couldn't tell if reasoning had happened or not until I turned on the reasoning summary

This piece thinks that the reason I got a crap pelican riding a bicycle from Opus 4.7 is that it didn't think about it first, I'm trying to …
I'm a big fan of the pelican GLM-5.1 drew me today, it even animated it! https://simonwillison.net/2026/Apr/7/glm-51/
I tried a 15MB, 30 page text-heavy PDF and Opus 4.7 reported 60,934 tokens while 4.6 reported 56,482 - that's a 1.08x multiplier, significan…
Pelicans for Meta's new Muse Spark models - plus I did a bit of a deep dive into the Code Interpreter and fascinating 'container.visual_grou…
Important to note: that 3x increase for images is entirely due to Opus 4.7 being able to handle higher resolutions. I tried that again with …
The new Qwen3.6-27B just gave me definitely the best pelican riding a bicycle I've had from a 16.8GB model file! https://simonwillison.net/2…

Source: Simon Willison (X) | 2026-04-21

Related