Hacker News Reader

nicoburnson 4-hour battery storage is cheaper to install than gas turbines all across globe

Four-hour grid-scale batteries wouldn't have helped the Texas winter crisis much. But something like a 10 or 20kwh home battery would have helped a lot (it wouldn't sustain normal energy usage for that long, but the individual home owner could choose to ration the available power for critical functions).

nicoburnson 4-hour battery storage is cheaper to install than gas turbines all across globe

You think the Oil and Gas industry is cleaner?

Recylable is important because it means we don't have to mine as much.

nicoburnson 2027 Web Platform Feature Ranking

https://blitz.is/wpt/css/css-gaps

So nobody's even started on it except Chrome.

nicoburnson 4-hour battery storage is cheaper to install than gas turbines all across globe

The cost of batteries has gone down somewhere between 60-80% over the previous 10 years (and my understanding is that trend is expected to continue due to a combination of new technologies (e.g. Sodium Ion) and increased scale). So that one seems totally reasonable. A little conservative if anything.

I can't comment on the cost of Gas Turbines.

nicoburnson Pop!_OS bans AI-generated code from much of its codebase

Yes, but it's the only option if you want to retain a maintainable code base. And you can always slow down. You'll probably still be a bit faster than you were before.

nicoburnson Pop!_OS bans AI-generated code from much of its codebase

Reasonable, although I've taken a different approach. Either closing such PRs, or treating them as very detailed issues and having my own LLM build the actual fix.

My repos probably don't see as much traffic as SQLAlchemy though.

nicoburnson Pop!_OS bans AI-generated code from much of its codebase

Were you reviewing the changes? I've seen lots of projects with this problem. But if AI PRs have to pass the same review bar as any other PR then it shouldn't be an issue in theory (if you can actually maintain the discipline).

nicoburnson One month coding with GLM 5.3 Flash

> You also know nothing about how I use electricity in my home

I don't

> Where I live isn't relevant,

But where you live does matter. Average monthly household energy usage in the EU is 200-400 kWh. In the US it's more like 800-900kWh. So what you consider "normal energy usage" may vary considerably by where you live.

At 200-400kWh total usage, 30kwh starts to look a lot more significant. So you should at least consider the possibility that it's not that energy usage from AI is insignificant, but that your existing energy usage is wasteful.

nicoburnson The Forgetful CPU (Linux on M4)

> here are talks of John Ternus potentially selling Apple Silicon for server and AI use.

At the very least they ought to consider doing a macOS-based server chip. Given how many providers are racking Mac Minis these days. It's mostly for CI testing for code deployed to Apple platforms, so it very much supports their business.

nicoburnson Bez: Generating a browser engine from specs and tests

I've tried most of them. Certainly all the Open AI and Anthropic models. Fable is still the best I've tried. But it still struggles with architectural issues.

nicoburnson How to speed up the Rust compiler in September 2026

> Linking is super slow even in debug

Linking is normally slower in debug btw (because of the debug info)

nicoburnson Bez: Generating a browser engine from specs and tests

Something like a 4k RGBA texture being 30mb and you need at least 2 for a swapchain. Of course you might not be rendering at 4k, but those are just output buffers before you even start counting application memory.

nicoburnson Bez: Generating a browser engine from specs and tests

Good idea - thanks.

FWIW:

- Binary sizes start around 8mb if you're using GPU rendering (you can go smaller with CPU rendering, but you probably want the GPU). Our full browser app which pulls in things like sqlite, http cache libraries, etc is 20mb. Those usually compress to about half for distribution (.dmg, .appimage, etc).

- Base memory usage is something like 100mb (mostly from the graphics stack). I'm hoping to be able to bring that down a bit, but I think you can't realistically get much lower than 60mb with modern graphics. And to be perfectly honest we currently have an issue for RAM where it will often jump to more like 300-400mb after a little use. And I haven't fully gotten to the bottom of that yet.

nicoburnson Bez: Generating a browser engine from specs and tests

That does happen, but these days they tend to add that kind of thing to the spec (and the test suite). There was a minor drama several years when WHATWG (representing browser vendors) effectively took over the spec process from the W3C because they were fed up with the W3C taking an idealistic viewpoint, and speccing things that they couldn't actually implement.

nicoburnson Bez: Generating a browser engine from specs and tests

I have a working (and not vibe coded) implementation of a "browser engine for apps": https://github.com/DioxusLabs/blitz

So far it's only HTML/CSS (and we have our Rust-based framework to write the apps in). But it has been designed for fast incremental rendering, so it could be extended with JavaScript support quite easily.

nicoburnson Bez: Generating a browser engine from specs and tests

As someone who has spent the last 3 years implementing a browser engine from scratch full time (that currently passes ~half the 200k "css" tests that test style/layout/rendering), I find that (without a lot of close hand holding) the AIs are very far from being able to do this. They'll give you something that passes the tests, but it will do it a ridiculous way be far too slow to be useful (and is wrong architecturally such that it's not going to converge on a better solution).

nicoburnson Micron CEO Says Memory Supply Will Be Much Tighter in 2027 and 2028 Than in 2026

Basically everyone I know who doesn't have a tech job is struggling for money / feels like the world is unaffordable for them atm. Those without jobs are struggling to get them. And those with jobs are scared to change even if they don't like them.

And from what I read in the media, a lot of the economic indicators are backing this up: discretionary spending is down, private debt levels are rising, etc. All signs that the slack in the system is disappearing.

nicoburnson Micron CEO Says Memory Supply Will Be Much Tighter in 2027 and 2028 Than in 2026

> LLMs require orders of magnitude more memory than we could have ever used before

That's true. But will anyone have any money to pay for the LLMs? The AI market is currently being heavily subsidised by, ultimately, everyone else. But the economy in general is looking extremely dire at the moment, and that seems unlikely to last.

nicoburnson Git 3.0's upcoming SHA-256 default will be a costly mistake

From what I'd read, SHA256 in git is showing every sign of being another IPv6. In particular:

- It's implemented in a non-backwards-compatible way

- The benefits over the older model are a bit nebulous

- There's a large amount of tooling that needs to catch up, and little sign that there is movement there

nicoburnson How to speed up the Rust compiler in September 2026

(I did a quick test, and I'm seeing between 15-20% for https://github.com/servo/stylo which is a macro-heavy crate. I guess it only matter for crates you're actually editing though, macro will already be cached as part of "entire crate is unchanged")

> Another thing that can easily improve performance is changing the global allocator, but I've seen teams that measured 10% perf improvements in their own metrics decide against going with anything other than the "default".

Yeah, although I think there's more of a trade-off there. Alternative allocators can add significant amounts of compile time. Whereas, modulo maturity, I think a faster linker is more of a pure win. I would imagine we will make wild the default linker at some point if development continues on the trajectory it seems to be on.

nicoburnson How to speed up the Rust compiler in September 2026

> For symbol heavy projects, linking is a surprising bottleneck.

Is that still true with modern linkers like `wild`? Seems like it can link Chromium in 1-2s.

> Another thing is that stable rust doesn't treat macros as idempotent

This seems absolutely insane to me given how pervasive macros are in Rust (I wonder how much of incremental compilation time is just repeated serde derives?). Obviously we can't just blindly treat all macros as idempotent, but an opt-in attribute on a macros that pinky-promises that it is seems like it ought to be pretty easy to implement?

Maybe somebody's looked into it and it doesn't help much? But I've heard (unverified) rumours of the opposite.

nicoburnson How to speed up the Rust compiler in September 2026

If you have fast enough hardware then Rust compile times are already not that big of a deal.

nicoburnson Vermont replacing power plants with home batteries

They're rated to last that long under a full charge-discharge cycle per day. You won't be using them more than that unless you're doing something really crazy.

nicoburnson Deser: Rethinking Rust Serialization

Facet set out to compile faster, but AFAIK it never actually achieved that goal.

nicoburnson Vermont replacing power plants with home batteries

> As a consumer, would you want the extra usage on your battery?

I feel like this is likely going to be a non-issue in practice. Because these batteries are rated to last at least 10 years either way. And by that time, the cost of replacement will be dramatically cheaper.

nicoburnson Sonnet 5.5

It was really verbose and pedantic. I'm sure that made it more thorough. But compared to Fable (which it wasn't much cheaper than) where you could get the same rigour and more with a lot more concision, it was a tough sell. 5.5 is a lot cheaper and seems a lot better balanced.

nicoburnson Sonnet 5.5

5 was definitely bad. 5.5 seems a lot better so far. But still not close to Fable in terms of quality.

nicoburnson The problem is not AI code, but not knowing about system architecture or intent

> I am finding this, professionally, not so dramatic - but mostly because the industries in which I've consistently shipped code at scale involve review as a first principle, as in no un-tested, un-reviewed code gets shipped,

> And having AI code to review is no different than any other code that ever was to review

If your company is sticking to "everything needs (human) review" then you wont run into most of this. This issue is that a lot of companies are using AI as an excuse to remove that review process (either partially or entirely).

nicoburnson Japan moves to tighten rules for foreigners

There are also 13.2 million pensioners. That's close to 20% of the population.

nicoburnson Samsung accidentally freezes its smart fridges with a software update

Aside: I heard that "eco mode" is typically not actually the most energy efficient mode on most washing machines. Apparently it's a standard mode they have to add so that energy efficiency can be measured across machines, but that means it can't be optimised.

You're typically better off looking for some kind quick/fast mode. Or even the "regular" mode.

(YMMV, look things up for your specific model)