The screenshot from the page itself (the split original/translated) does not translate the image labels. Is that on purpose? It only translates text and does not do OCR?

I remember people using Yahoo and AltaVista a lot. And before gmail everyone had a yahoo email (if they didn't already have a hotmail). Times change, kings fall from grace.

Google has been the dominant force for about 80% of the internet’s existence. I understand things come and go, but Google is incredibly unique. Their importance cannot be overstated

Yes but they were mainly a force of evil. Despite their old motto. They made the internet everything it is today, a hellscape of tracking, advertising and other monetisation.

None of this is an endorsement of the company - I am almost done de-googling my life. They are terrible.

It doesn’t change the fact that they literally impacted the trajectory of how the internet developed in a very obvious, concrete way.

xhigh tells it to overthink and re check everything. Low tells it to only do the minimum thinking necessary. I would suggest to give qwen medium which doesn't inject any thinking directives into it and also to give as much context as you can, ideally around 500k tokens or even 1M if you can. Big complex tasks like these make the model hit the compaction trigger a lot and they end up re thinking the same thing several times in my experience.

Doesn’t it max out its context at like 256k?

It supports YaRN. From the model card: "Context Length: 262,144 natively and extensible up to 1,010,000 tokens."

But, ~256k is all I can fit on my dual 32GB setup, and it gets slow as heck at 256k, anyway. I think just convincing it to chew less and do more is probably the right solution for Qwen 3.8 27B, though I guess we need some benchmarks to get the feel for how much intelligence you lose by choosing a lower reasoning level.

I think /handoff on pi (or at least oh my pi) is what you are looking for