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.

Comments URL: https://news.ycombinator.com/item?id=47054219

Points: 2

# Comments: 0

But I'm now facing the problem that LLM agents don't like this, and when I instruct them to run certain tools, they remove the leading comma. It's normally fixed with one extra sentence in the prompt, but still inconvenient.

I think this is something people ignore, and is significant. The only way to get good at coding with LLMs is actually trying to do it. Even if it's inefficient or slower at first. It's just another skill to develop [0].

And it's not really about using all the plugins and features available. In fact, many plugins and features are counter-productive. Just learn how to prompt and steer the LLM better.

[0]: https://ricardoanderegg.com/posts/getting-better-coding-llms...

Comments URL: https://news.ycombinator.com/item?id=46777146

Points: 1

# Comments: 0

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.

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

Comments URL: https://news.ycombinator.com/item?id=46710611

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46699021

Points: 3

# Comments: 0

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`.

Comments URL: https://news.ycombinator.com/item?id=46617033

Points: 2

# Comments: 1

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

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

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.

Comments URL: https://news.ycombinator.com/item?id=46359882

Points: 1

# Comments: 0

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.

Comments URL: https://news.ycombinator.com/item?id=46352234

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46344528

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46265811

Points: 161

# Comments: 49

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