Aeolos

This sounds super interesting. Do you have any blog or pointers where I could read more about this?

Fortunately, multiple model providers are offering open weights models at significantly lower prices than closed models.

It focuses on training and data provenance, rather than serving.

Humans fail in infinitely more complicated ways than LLMs. They can have a difficult personality, a medical issue, family stress, hangover, sleep deprivation or they can just wake on the wrong side of the bed. On any given day, you never know if you will get an expert in domain X or a sleep-deprived version of the same that accidentally drops a database.

Indeed, if you remember before AI took the world by storm, HN used to be chock-full of articles about how the hiring process is broken for both employers and candidates, where you can never tell if what you see is what you get.

When I run a local LLM I get none of that. I hit the intelligence walls or buggy behaviour, but it doesn't matter if it's 8am or 8pm, the model behaves exactly the same. If something doesn't work as I wished, I can retry as many times as I wanted without the model getting angry at me.

On the other hand, an American company can sell your chats to adtech/insurance/your government in ways that can harm you quite directly. Something worth considering.

Previously discussed here: https://news.ycombinator.com/item?id=33770277

UB supersedes volatile, once the compiler hits UB then all bets are off. Compilers can and do optimize out UB branches, which is almost never what you want... yet here we are.

https://fishshell.com/blog/rustport/

95% of the test suite is passing today, so it's pretty close: https://github.com/uutils/coreutils-tracking/blob/main/gnu-r...

There is a list of open items here, it's looking pretty good tbh: https://github.com/orgs/uutils/projects/1

It is not, from a statistical perspective.

In my experience, curiosity and intelligence are very strongly correlated. There is a real gap between people with the curiosity and ability to explore and learn, and people without. This is often handwaved as "motivation" but it's more than just that.

In fact, the gap is so large that it can be really hard for a person on one side of it to understand how people on the other side think.

Why is that?

As a counterpoint, I found GPT 4.5 by far the most interesting model from OpenAI in terms of depth and width of knowledge, ability to make connections and inferences and apply those in novel ways.

It didn't bench well against the other benchmaxxed models, and it was too expensive to run, but it was a glimpse of the future where more capable hardware will lead to appreciably smarter models.

Yeah, but as the HTMX author said, HTMX sucks! Definitely should use Datastar!

Yet they were not - why is that?

How do you deal with slow compilation times?

I very much think that AIs with minds are possible

The real question here is how would _we_ be able to recognize that? And would we even have the intellectual honesty to be able to recognize that, when at large we seem to be inclined to discard everything non-human as self-evidently non-intelligent and incapable of feeling emotion?

Let's take emotions as a thought experiment. We know that plants are able to transmit chemical and electrical signals in response to various stimuli and environmental conditions, triggering effects in themselves and other plants. Can we therefore say that plants feel emotions, just in a way that is unique to them and not necessarily identical to a human embodiment?

The answer to that question depends on one's worldview, rather than any objective definition of the concept of emotion. One could say plants cannot feel emotions because emotions are a human (or at least animal) construct; or one could say that plants can feel emotions, just not exactly identical to human emotions.

Now substitute plants with LLMs and try the thought experiment again.

In the end, where one draws the line between `human | animal | plant | computer` minds and emotions is primarily a subjective philosophical opinion rather than rooted in any sort of objective evidence. Not too long ago, Descartes was arguing that animals do not possess a mind and cannot feel emotions, they are merely mimicry machines.[1] More recently, doctors were saying similar things about babies and adults, leading to horrifying medical malpractice.[2][3]

Because in the most abstract sense, what is an emotion if not a set of electrochemical stimuli linking a certain input to a certain output? And how can we tell what does and what does not possess a mind if we are so undeniably bad at recognize those attributes even within our own species?

[1] https://en.wikipedia.org/wiki/Animal_machine

[2] https://en.wikipedia.org/wiki/Pain_in_babies

[3] https://pmc.ncbi.nlm.nih.gov/articles/PMC4843483/

Or when you enable optimizations and since accessing an object with invalid state is UB, the compiler helpfully decides it is now permitted to format your hard drive.

https://gcc.gnu.org/legacy-ml/gcc/2016-02/msg00381.html

"The fact is, undefined compiler behavior is never a good idea. Not for serious projects."

Almost all open-source software comes with a version of the following license terms:

"THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE."

To use the software you have to accept the license, which means you explicitly confirm that they are not your supplier. Pretty clear cut, no?

Edit: EULA-loving companies don't want to accept the license terms for the _free_ software they themselves are using - the hypocrisy is nothing short of staggering.

It's about as useful as your complaining.

Good riddance for Lightning.

And just like that, OpenAI got banned in my company today.

Good job.

Not the grandparent, but Airflow is painfully slow and inefficient.

Our reinvented wheel using posgresql, rabbitmq and EC2 runners has ~10x better throughput and scales linearly with the number of pending tasks, whereas the airflow falls apart and fails to keep the runners fully occupied the moment you out any real load on it.

GraphQL APIs can easily DOS your backend if you don't configure extra protections (which are neither bulletproof nor enabled by default), they suffer from N+1 inefficiencies by default unless you write a ton of extra code, and they require extra careful programming to apply security rules on every field which can get very complex very fast.

On the plus side, it does have offer communication advantages if you have entirely independent BE and FE teams, and it can help minimize network traffic for network-constrained scenarios such as mobile apps.

Personally, I have regretted using GraphQL every time.

Given the dramatic uptake of Cursor / Windsurf / Claude Code etc, we can be 100% certain that LLM companies are using LLMs to improve their products.

The improvement loop is likely not fully autonomous yet - it is currently more efficient to have a human-in-the-loop - but there is certainly a lot of LLMs improving LLMs going on today.

It's almost as if this is a non-human intelligence, which presents different strengths and weaknesses than human intelligence.

Is that really so surprising, considering the tremendous differences in underlying hardware and training process?

As much as I loathe diving into the utter cesspool of US politics, I do need to point out that the article is simply quoting the goals of Project 2025, which prominently include:

to “defang and defund the woke culture warriors who have infiltrated every last institution in America”.

You are pretending that Nature is the one who cares about DEI, when in fact it is the Project 2025 partisans who made this their flagship concern. This comes across as quite dishonest.

Ahhh, yes, the Great War of 2021 when the US invaded Sweden, Finland, and Norway for having governments in power that have far more than “even the slightest socialist tendencies”.

No, the Great Stupidity of 2025, when the US started officially endorsing the extreme right-wing in the EU and calling for its dismantlement.

Yet in practice this works fine for all intents and purposes.

Sure, you might get a loading error if you try to run your Ubuntu 24.04-compiled executable on Ubuntu 18.04 if you use the default toolchain. tTat’s exactly the same as C or C++, only much easier to fix in rust by rustup-installing the right tool chain.

Compiling on Ubuntu 18.04 and running on 24.04 is absolutely not an issue. Same for windows.

In practice this is really not a problem, especially for cargo libraries that you anyway build from source.

Elon Musk [...] created Tesla

Elon Musk did not found Tesla, and most definitely did not did it for environmental reasons.

"Tesla was incorporated in July 2003 by Martin Eberhard and Marc Tarpenning as Tesla Motors." [1]

"If, I don’t know, 50 to 100 years from now, we’re mostly sustainable. I think that’ll probably be okay. So it’s not like the house is on fire immediately. [...] "The risk is not as high as a lot of people say it is with respect to global warming." [2]

[1] https://en.wikipedia.org/wiki/Tesla,_Inc.

[2] https://turboscribe.ai/transcript/share/4422534834081521519/...

Not the same poster, but I am using Axum (webserver) + Maud (templating engine) + SeaORM (db adapter) + HTMX and I'm finding the end-result highly productive.

Even though Rust is more verbose, and SeaORM has a few quirks, I am making faster progress in Rust than my existing mature Typescript + Node + apollo-graphql + ReactJS setup. Once I was over the initial setup & learning curve (about a week), I find myself able to spend more time on business logic and less time hunting runtime bugs and random test failures. There's something almost magical about being able to refactor code and getting it up and running in a matter of minutes/hours, compared to days for similar operations in Typescript.

It's definitely still a young ecosystem that desperately needs a Django equivalent (loco.rs is worth keeping an eye out, but it's not there yet.) But I'm willing to tackle a bit of immaturity & contribute upstream to avoid the constant needless churn of the js world.

With rust, I treat compiler errors as ultra-fast unit tests. I share the same experience: once it compiles, 99.9% it works fine on first try. It's a wonderful development experience.