HNHacker News
TopNewBestAskShowJobs

the_duke

17,811 karma · joined June 4, 2016

submissionscomments
the_duke··on GPT‑5.3‑Codex‑Spark
They claim the opposite, though, saying the chip is designed to tolerate many defects and work around them.
the_duke··on How to effectively write quality code with AI
That's because many developers are used to working like this.

With AI, the correct approach is to think more like a software architect.

Learning to plan things out in your head upfront without to figure things out while coding requires a mindset shift, but is important to work effectively with the new tools.

To some this comes naturally, for others it is very hard.

the_duke··on GPT-5.3-Codex
I do not trust the AI benchmarks much, they often do not line up with my experience.

That said ... I do think Codex 5.2 was the best coding model for more complex tasks, albeit quite slow.

So very much looking forward to trying out 5.3.

the_duke··on Claude Code is suddenly everywhere inside Microsoft
Do you have a source for that?
the_duke··on Benchmarking OpenTelemetry: Can AI trace your failed login?
This is very confusingly written.

From the post I expected that the tasks were about analysing traces, but all the tasks in the repository are about adding instrumentation to code!

Some of the instructions don't give any guidance how to do it, some specify which libraries to use.

"Use standard OTEL patterns" ... that's about as useful as saying "go write some code". There are a lot of ways to do instrumentation....

I'd be very curious HOW exactly the models fail.

Are the test sets just incredibly specific about what output they except, and you get a lot of failures because of tiny subtle mismatches? Or do they just get the instrumentation categorically wrong?

Also important: do the models have access to a web search tool to read the library docs? Otel libraries are often complicated to use... without reading latest docs or source code this would be quite tricky.

Some models have gotten better at adding dependencies, installing them and then reading the code from the respective directory where dependencies get stored, but many don't do well with this.

All in all, I'm very skeptical that this is very useful as a benchmark as is.

I'd be much more interested in tasks like:

Here are trace/log outputs , here is the source code, find and fix the bug.

the_duke··on De-dollarization: Is the US dollar losing its dominance? (2025)
According to USTR data the EU had a 200bn goods surplus, but a 100bn services deficit in 2024.

So a 100bn deficit out of 800bn total US imports.

The deficit is there, but it's not nearly as lopsided as some reporting would have you believe.

the_duke··on Article by article, how Big Tech shaped the EU's roll-back of digital rights
Tell that to all the companies that built their entire tech stacks on US cloud providers...

Massive endeavor for a lot of setups.

the_duke··on I switched from VSCode to Zed
The more advanced AI related workflows are the reason I finally switched away from neovim as my main coding IDE - for now.

The existing AI plugins for neovim aren't great.

the_duke··on Manus AI 100M USD ARR
With a bit of education one would know that manus is Latin for hand. That's where "manual" comes from.

And their logo is, lo and behold ... a hand!

the_duke··on AI will make formal verification go mainstream
I've been preaching similar thoughts for the last half year.

Most popular programming languages are optimized for human convenience, not for correctness! Even most of the popular typed languages (Java/Kotlin/Go/...) have a wide surface area for misuse that is not caught at compile time.

Case in point: In my experience, LLMs produce correct code way more regularly for Rust than for Js/Ts/Python/... . Rust has a very strict type system. Both the standard library and the whole library ecosystem lean towards strict APIs that enforce correctness, prevent invalid operations, and push towards handling or at least propagating errors.

The AIs will often write code that won't compile initially, but after a few iterations with the compiler the result is often correct. Strong typing also makes it much easier to validate the output when reviewing.

With AIs being able to do more and more of the implementation, the "feel-good" factor of languages will become much less relevant. Iteration speed is not so important when parallel AI agents do the "grunt work". I'd much rather wait 10 minutes for solid output rather than 2 minutes for something fragile.

We can finally move the industry away from wild-west languages like Python/JS and towards more rigorous standards.

Rust is probably the sweet spot at the moment, thanks to it being semi-popular with a reasonably active ecosystem, sadly I don't think the right language exists at the moment.

What we really want is a language with a very strict, comprehensive type system with dependent types, maybe linear types, structured concurrency, and a built-in formal proof system.

Something like ADA/Spark, but more modern.

the_duke··on I tried Gleam for Advent of Code
What you are saying is: no, it doesn't.

Of course dynamic dispatch can be implemented in almost every language. The Linux kernel uses dynamic dispatch with C!

But that's a hack, not a language feature.

the_duke··on SQLite JSON at full index speed using generated columns
Would love a Rust implementation of this.
the_duke··on Thoughts on Go vs. Rust vs. Zig
To be fair, you can enforce this just by filling all the allocated memory with zero, so it's possible to fail at startup.

Or, even simpler, just turn off over-commit.

But if swap comes into the mix, or just if the OS decides it needs the memory later for something critical, you can still get killed.

the_duke··on Advent of Code 2025
I use AoC as a chance to try a new language every year.

In the past I used it to try out Swift, J, R, ...

the_duke··on Advent of Code 2025
LLMs, and especially coding focused models, have come a very long way in the past year.

The difference when working on larger tasks that require reasoning is night and day.

In theory it would be very interesting to go back and retry the 2024 tasks, but those will likely have ended up in the training data by now...

the_duke··on Trillions spent and big software projects are still failing
The accounting, legal and business process requirements are vastly different at different scales, different jurisdictions, different countries, etc.

There's a crazy amount of complexity and customizability in systems like ERPs for multinational corporations (SAP, Oracle).

When you start with a small town, you'll have to throw most of everything away when moving to a different scale.

That's true for software systems in general. If major requirements are bolted on after the fact, instead of designed into the system from the beginning, you usually end up with an unmaintainable mess.

the_duke··on Meta Segment Anything Model 3
Side question: what are the current top goto open models for image captioning and building image embeddings dbs, with somewhat reasonable hardware requirements?
the_duke··on Building more with GPT-5.1-Codex-Max
The key is learning how to provide proper instructions.

Treat it as a developer that just joined the project and isn't aware of the conventions.

Provide hints for the desired API design, mention relevant code locations that should be read to gain context on the problem, or that do similar things.

An AGENTS.md that explains the project and provides some general guidelines also helps a lot.

Codex can be incredibly strong when prompted the right way.

the_duke··on Building more with GPT-5.1-Codex-Max
I bet they just wanted to counter Gemini 3 and stay on top of the leaderboards for coding, and were preparing this for a while to push out alongside Gemini 3.
the_duke··on Blue Origin lands New Glenn rocket booster on second try
A lot of SpaceX employees went over to Blue Origin over the years, so there also was a lot of knowledge transfer and Blue could capitalize on the iterations of SpaceX.
the_duke··on Heartbeats in Distributed Systems
Raft is a consensus protocol, which is very different from a gossip protocol.
the_duke··on Heartbeats in Distributed Systems
Two interesting papers:

* Epidemic broadcast trees: https://asc.di.fct.unl.pt/~jleitao/pdf/srds07-leitao.pdf

* HyParView: https://asc.di.fct.unl.pt/~jleitao/pdf/dsn07-leitao.pdf

The iroh-gossip implementation is based on those: https://docs.rs/iroh-gossip/latest/iroh_gossip/

the_duke··on We cut our Mongo DB costs by 90% by moving to Hetzner
The cloud console is pretty good though? Even does live sync!

The old one for dedicated servers (robot) is horribly outdated though.

the_duke··on OpenAI Moves to Complete Potentially the Largest Theft in Human History
Surely the money coming in would otherwise have been investments exchanged for stock, which are not taxed until gains are realized.
the_duke··on Hard Rust requirements from May onward
Defaults and ecosystem approach matter a lot, though.

The whole Rust ecosystem is heavily biased towards prioritising memory safety and "safe by construction" .

This is evident in the standard library, in how crates approach API design, what the compilation defaults are, ...

In 6+ years of using Rust the only time I had to deal with segfaults was when working on low level wrappers around C code or JIT compilation.

Zig has some very interesting features, but the way they approach language and API design leaves a lot of surface area that makes mistakes easy.

the_duke··on Hard Rust requirements from May onward
Anyone capable of programming and willing to invest enough time will be able to learn Rust, in my opinion.

It might take some people months rather than days, but I think that is a desirable outcome.

Important low level software should be written by competent developers willing to invest the effort.

the_duke··on AWS to bare metal two years later: Answering your questions about leaving AWS
GCP is pretty good though, considering the complexity.

Azure is ... a different story...

the_duke··on Rust cross-platform GPUI components
Ah, thanks for the hint.

I indeed was not enabling it.

I'll give it a try!

the_duke··on Rust cross-platform GPUI components
Even in Dioxus the usefulness is somewhat limited right now though.

(dioxus-7-rc.3)

It usually only works when reordering elements, or changing static values (styles, attributes, etc).

Which, to be fair, does speed things up a lot when tinkering with small details.

But 70%+ or so of my changes still result in recompiles.

the_duke··on Rust cross-platform GPUI components
Virtualized lists and tables are amazing!

So many UI frameworks don't have these and require building them yourself...

← PreviousPage 3 of 34Next →