Benchmarks don’t really tell you much. For API best will always be a model+effort sweep on your internal evals (and if you don’t have internal evals, do that first).

For individual coding harnesses, honestly I just go with vibes. The best workflow is the one that works for you.

I wish Apple would make a similar device. I'm fine with recycled chips and getting a bit gimped on RAM size.

Like the MacBook Neo of iPads; I just really want a media consumption device. A20 Pro means nothing to me.

It also doesn't help that a lot of scammers use this, or fake cyber incidents, for phishing; so it's not like they have an easy solution for exempting "security emails" either.

Maybe it’s 1% or 10% today, but a decade ago, having/assembling the technical chops to know how to build something was a huge part of the meat / barrier to entry.

US commercial interest =/= OpenAI and Anthropic.

^Not recommended literally due to brownouts/etc, but a cheap power management IC on a breadboard can solve that. Alternatively, add a battery/etc.

Home solar panels and batteries are just like this except on a bigger scale; and with (hopefully) more QC.

Ask your agent to make you a visualisation, heat map, whatever. I bet it's just that you're using these models more, and for more complex tasks.

Compute, data, and parameter count are the three logarithmic values that correspond to model performance.

So if you find ways of improving training efficiency (the simplest conceptually is probably local/global sliding window attention like Gemma; the latest DeepSeek and Kimis have quite fancy ones), you will be able to have more effective compute, and train smarter models while keeping data and param count the same.

If you find this fascinating and want to dive more, I encourage checking out nanochat (solid GPT-2 repro; minimal LoC); and trying to make architectural tweaks with a coding agent.

“Learning through experimentation” has never been easier or more fun in my opinion. If you have a GPU, even an older 8GB card (or a few bucks for Runpod), you can pretrain your own small language model and start experimenting / tweaking it.

Still get the model out there.

These defenders aren’t supposed to have access to the “defender models”.

Comments URL: https://news.ycombinator.com/item?id=50202345

Points: 3

# Comments: 0

> Moreover, because iOS apps are sandboxed, as implemented in other jurisdictions, apps available through alternative distribution will be sandboxed, which further strengthens security and reduces the likelihood that any app will compromise other apps [...]

First, Apple does not follow the same rules they set for developers.

Second, Apple does not treat all developers equally. We have functionality we’re unable to offer to iOS users.

The same feature, including technical implementation mechanism, is available in Claude and Gemini. It’s unfair.