bla3

It's alright.

This sounds roughly right to me, except for "maintainability". In my experience, agents really don't like deleting code unless you explicitly ask for it. If you're not careful, you end up with new better implementations of things but with the old implementation still around in perpetuity. Humans do this too of course.

If you're reading this and you're put off by the "uses an LLM", don't be. This is not a low-effort video, quite the opposite. This is one of the best YouTube videos I have ever seen.

Mirrors my experience: LLMs are really good at optimizing, better than most humans. But also, they tend to not reach absolute peak performance where people made an effort to optimize something.

Since most problems see fairly little optimization, that's still a big win most of the time.

> I built one, by porting Boehm’s engine. > It’s 2026, so I didn’t hand-write the port. I directed Opus 4.8 to translate the source line by line into Swift

I wish I could filter out stuff like this. Cool work by Hans Boehm, but what's the value add in this blog post.

This is the mindset that gives you Java-Style GUIs.

I don't think they trust Gemini as they run that on-device or on-site, on Apple's own servers.

See also https://security.apple.com/blog/private-cloud-compute/

I love the recently added "In Response to Hacker News" section.

> "can't make 9 babies in a month"

It's "9 women can't make a baby in one month".

I like to think everyone came to the conclusion that it would strengthen the piece if most comments on it appear to miss the point and are slightly robotic.

https://arstechnica.com/gadgets/2026/02/how-to-downgrade-fro... describes how to downgrade.

Since then, Swift also grew excellent C++ interop, something Rust doesn't have at all.

It's a shame that JpegXL doesn't have a freely available spec.

If they use Rust for new code and C++ changes are all in old code, this could be explained just by older code being more risky to change.

There was a ton of backlash when Glass launched. Search for "glassholes" to find articles on that topic from back then.

Why do Hunyuan, OpenAI 4o and Gwen get a pass for the octopus test? They don't cover "each tentacle", just some. And midjourney covers 9 of 8 arms with sock puppets.

I think that might be true of the language committee, but there's presumably a huge crowd of people with existing c++ code bases that would like to have a different path forward than just hoping that the committee changes priorities.

The "Possible routes forward" section in the linked post mentions this suggestion, and why the author doesn't love it.

Sounds like they compile rust to wasm, so regular wasm instead of WasmGC is probably enough for them.

WebP lossless is close to state of the art and widely available. It's also not widely used. The takeaway seems to be that absolute best performance for lossless compression isn't that important, or at least it won't get you widely adopted.

That's a critique of `async`, not of `using` though, right? This doesn't seem to make functions more colored than they already are as far as I understand.

In my experience they're not great with mathy code for example. I had a function that did subdivision of certain splines and had some of the coefficients wrong. I pasted my function into these reasoning models and asked "does this look right?" and they all had a whole bunch of math formulas in their reasoning and said "this is correct" (which it wasn't).

How does this compare to https://jcgt.org/published/0011/03/04/paper.pdf? It seems superficially pretty similar.

The pictures on the wall change too.

> The AI Futures Project is a small research group forecasting the future of AI, funded by charitable donations and grants

Would be interested who's paying for those grants.

I'm guessing it's AI companies.

Exactly. New image models are always exciting for two weeks or so. New LLM models are useful until the next,. better model comes out.

Which probably is just a small integer multiple of two weeks, but hey!

Because it leaks the device type of your messaging partner.

Really shows how apple is only into privacy when it's self-serving.

Similar to hixie's https://docs.google.com/document/d/1peUSMsvFGvqD5yKh3GprskLC...

I wonder if we're starting to see the effects of the mass exodus a while ago.