I find this a very exciting release. I was actually hoping we would somehow get macOS on mobile 'A' chips some day. And I think this is better than putting 'M' chips on an iPad.

My iPad with an 'M1' chip actually consumes more battery than much older iPads when both are locked and with the screen off. I ended up figuring it was probably because, in the 'M' chip, the lowest possible energy usage is way higher than the 'A' chip. So even small background wake-ups used more energy.

I'm still hoping one day we have an iPad with macOS.

I share the same feeling. I waited as much as possible to upgrade to iOS 26 / macOS Tahoe.

Two days ago, I finally upgraded. Liquid Glass is one of the worst things I've ever seen in terms of design. It reminds me of when I personalized old cheap android phones or Linux distros just "to look cool". Cool-looking: yes. Unusable: also yes. Tasteful design: almost absent.

Just the increase of the border-radius in all elements makes it hideous. Apps with a search bar on a scrollable list look like a CSS bug when the search bar is on top of the elements. Neither the search bar nor the element underneath are visible. Although this applies to most transparency effects on Liquid Glass. Neither the elements above nor below the "glass" are visible. And the extra value added is zero.

The thing is, I can still adapt to it, or tweak transparency and contrast. But I've seen elderly relatives struggle just because WhatsApp decided to add the "Meta AI" floating button. I can't imagine what this "inaccessible" UI changes can do.

It is the first time I am trying to skip a macos version. I really hope in macos27 they will fix things. I used to skip every second windows version, so back here we are.

same here. using mac since OS9, and Tahoe is the first time i skipped a version (downgrade after 2 months)

Don't forget that if you're using SQLite on something like EBS, multiple queries may not be efficient.

I'm saying this as a huge SQLite fan, but also beware of what kind of storage you're using in your instance.

Yeah, you really want directly connected NVME drives to your machine/VPS. It can make orders of magnitude difference.

I've been using z.ai models through their coding plan (incredible price/performance ratio), and since GLM-4.7 I'm even more confident with the results it gives me. I use it both with regular claude-code and opencode (more opencode lately, since claude-code is obviously designed to work much better with Anthropic models).

Also notice that this is the "-Flash" version. They were previously at 4.5-Flash (they skipped 4.6-Flash). This is supposed to be equivalent to Haiku. Even on their coding plan docs, they mention this model is supposed to be used for `ANTHROPIC_DEFAULT_HAIKU_MODEL`.

Same, I got 12 months of subscription for $28 total (promo offer), with 5x the usage limits of the $20/month Claude Pro plan. I have only used it with claude code so far.

This offer was so stupid cheap there was no point in NOT getting :D

Do they still have that promo offer?

Looks like they have something for 29 USD with 3x the claude code usage: https://z.ai/subscribe

How has the performance been lately? I heard some people say that they change their limits likely making it almost not useable

Never had any problems with Z.ai models.

However they are using more thinking internally and that makes them seem slow.

Not sure about the impact of these, I guess it depends on the context where this engine is used. But there seems to be already exploits for the engine:

https://x.com/itszn13/status/2003707921679679563

https://x.com/itszn13/status/2003808443761938602

A few comments mentioning distillation. If you use claude-code with the z.ai coding plan, I think it quickly becomes obvious they did train on other models. Even the "you're absolutely right" was there. But that's ok. The price/performance ratio is unmatched.

I had Gemini 3 Flash hit me this morning with "you're absolutely right" when I corrected it on a mistake it did. It's not conclusive of anything.

That's interesting, thanks for sharing!

It's a pattern I saw more often with claude code, at least in terms of how frequently it says it (much improved now). But it's true that just this pattern alone is not enough to infer the training methods.

Or it’s conclusive of an even broader trend!

I imagine - and sure hope so - everyone trains on everything else. Distillation - ofc if one has bigger/other models providing true posterior token probabilities in the (0,1) interval (a number between 0 and 1), rather than 1-hot-N targets that are '0 for 200K-sans-this-token, and 1 for the desired output token' - one should use the former instead of the latter. It's amazing how as a simple as straightforward idea should face so much resistance (paper rejected) and from the supposedly most open minded and devoted to knowing (academia) and on the wrong grounds ('will have no impact on industry'; in fact - it's had tremendous impact on industry; better rejection wd have been 'duh it is obvious'). We are not trying to torture the model and the gpu cluster to be learning from 0 - when knowledge is already available. :-)

>Even the "you're absolutely right" was there.

I don't think that's particularly conclusive for training on other models. Seems plausible to me that the internet data corpus simply converges on this hence multiple models doing this.

...or not...hard to tell either way.

I enjoyed the post. I was about to link the "Let Me Speak Freely" paper and "Say What You Mean" response from dottxt, but that's already been posted in the comments.

I'm a huge fan of structured outputs, but also recently started splitting both steps, and I think it has a bunch of upsides normally not discussed:

1. Separate concerns, schema validation errors don't invalidate the whole LLM response. If the only error is in generating schema-compliant tokens (something I've seen frequently), retries are much cheaper.

2. Having the original response as free text AND the structured output has value.

3. In line with point 1, it allows using a more expensive (reasoning) model for free-text generation, then a smaller model like gemini-2.5-flash to convert the outputs to structured text.

A frozen dictionary would be very welcome. You can already do something similar using MappingProxyType [0]

  from types import MappingProxyType
  
  d = {}
  
  d["a"] = 1
  d["b"] = 2
  
  print(d)
  
  frozen = MappingProxyType(d)
  
  print(frozen["a"])
  
  # Error:
  frozen["b"] = "new"

[0]: https://docs.python.org/3/library/types.html#types.MappingPr...

> You can already do something similar

Only if you deny access to the underlying real dict.

Yes, this only prevents the callee from mutating it, it can't provide a strong guarantee that the underlying mapping won't be changed upstream (and hence MappingProxyType can't be washable).