Is it always May 10 in the countries where it's now? In Spain is the first Sunday of the month.

Second Sunday of May in the US

It seems it must be the same in Switzerland where I live, makes sense!

Why do they do this? Why not just have a fixed date for these things? Is it so people can use the weekend to celebrate?

If it was a fixed day it would end up being a week day a lot of the time.

Maybe that doesn’t matter, but it’s nice to have on a weekend.

Maybe I’m missing what you mean?

For Mother's Day, possibly, but it's not always the case. Thanksgiving is on the 4th Thursday of November.

Yes

Like in Portugal, I guess it is an Iberian thing.

In Poland it's on 26th of May.

People also have the right to question your decision. Freedom goes both ways.

He just missed the most important ones: America First, improving the economy and end wars.

Most tasks do not require frontier models, so as long as these models cover 95-99 per cent of the tasks, closed frontier models can be left for niche and specialized cases that are harder.

Frontier models can hardly do the tasks I want them too, I simply cannot buy into this notion.

For instance?

I am curious about it producing less tokens except for the max mode. I love DeepSeek V4 Flash and I use it extensively, it's so cheap I can use it all day and still not use all my 10$ OpenCode Go subscription. I use it always in max mode because of this, but now I wonder whether I should rather use high.

What do you use it for? I tend to just stick to SOTA (Claude 4.7 Max thinking), and put up with the slow req/response. I'm not sure what type of work i'd trust a less thinking model, as my intuition is built around what Claude vSOTA Max can handle.

Nonetheless eventually i want to build an at-home system. I imagine some smaller local model could handle metadata assignment quite well.

edit: Though TIL Mac Studio doesn't offer 512GB anymore... DRAM shortage lol. Rough.

I am experimenting with some game development and my thesis' beamer. I have a 20$ Codex account and I use GPT-5.5 for planning and DeepSeek for executing in OpenCode. This makes my Codex 5h tokens to last more than 10 minutes.

Apple just dropped the 128GB option as well.

It is still available for the M5 Max Macbook Pro, but yes, the Mac Studio is now only offered with up to 96 GB.

On max it uses more than twice as many tokens as on high when running the ArtificialAnalysis benchmark suite, and then it's indeed the model with the highest token usage (among the current top tier models). See the "Intelligence vs. Token Use" chart here:

https://artificialanalysis.ai/models?models=gpt-5-5%2Cgpt-5-...

Wow, the difference is quite considerable and the gain in intelligence is not that much. I might try to use high and just iterate more often. I am working with hobby stuff so I don't have to worry whether it breaks things or not.

How has opencode go been for you? Worth changing over from Claude pro?

I've found that opencode and codex are the two subscriptions that still seem to subsize usage. Deepseek V4 has been the most powerful model in opencode IMO, I trust it with problems where I can validate the solution such as debugging an issue - but I only trust the proprietary GPT-5.5 and Claude Opus 4.7 models for writing code that matters.

Given the price, extremely satisfied, especially thanks to DeepSeek V4 Flash that makes it last forever. I use it on top of my 20$ Codex which is great but tokens last nothing.

Gemini models, even if not so good at coding, are also competitive with GPT-5.5 and Claude Opus 4.7 in a lot of tasks while having considerably less parameters.

Outside of programming, I haven't gotten a good response from Opus (4.6 or 4.7). Optics, finance, and economics questions. All had glaring oversights. 5.5 is the strongest and very thorough. 3.1 comes very close, and while less thorough, it completes the response in <2 min while 5.5 will spend 15-20 minutes.

Which begs the question, where would 3.1 be if google let it run for 20 minutes on a prompt? Possibly worse, but you have to wonder.

Did you compare it with Kimi K2.6 and DeepSeek V4 Pro? I feel they're similar but as GLM is more expensive, I am not using it much.

I am using both on OpenCode Go plan and they're pretty good, but I would say still not at the same level at GPT-5.5 in my experience, I don't know about Opus.

On a different note, is Ollama cloud good?

> is Ollama cloud good?

I'd say they have reliability issues but for the price it's worth it.

I like that usage isn't measured per token but per computation time, which means that you get more usage when models become more efficient.