HNHacker News
TopNewBestAskShowJobs

Aeolos

1,064 karma · joined December 15, 2015

submissionscomments
Aeolos··on Google fixed more Chrome bugs in June than over the past two years, thanks to AI
The Rust type system helps you catch logic errors at compile time. Same with Haskell or Ocaml.
Aeolos··on DeepSeek pause fundraise after comments on compute gap to US leaked (transcript) [pdf]
Many people have tried before, but the bitter lesson has come for them all.
Aeolos··on Claude Opus 5
There used to be a time when you had to write in assembly and count bytes to fit your code into the vanishingly small ROM you had available.

Nowadays, you can just write in python with no care for the hundreds of thousands of cycles and megabytes of memory you are wasting.

All indications today point towards the same happening with the cost of intelligence.

Aeolos··on Claude Opus 5
I don't know, the CEO of Anthropic has openly said that each model by itself is profitable, they just reinvest everything into training more and more expensive models.
Aeolos··on Claude Opus 5
Reminds of a some programmers and researchers I know...
Aeolos··on Claude Opus 5
What if they spent 15 minutes doing that? Would you care then?

Scale matters a _lot_.

Aeolos··on Claude Opus 5
It's mimicking humans only in as far as it is still using tools & programming languages developed by humans, for humans.

This is temporary. There is a future where AI builds tools made by AI for AI, evolving at speeds that we may no longer be able to follow.

Even with our current nascent technology, we can already observe this happening. See the recent laments on the AI Bun rewrite that "it's a million lines of code that nobody has ever reviewed." Or Cursor building a new source-control system for LLMs, because git is designed for human collaboration speed, not hundreds of changes per second.

That's just 4 years in. How much of humanity's code will remain hand-written vs LLM-written 2, 5, 10 years from now?

Aeolos··on The Tower Keeps Rising
This sounds super interesting. Do you have any blog or pointers where I could read more about this?
Aeolos··on Anthropic's Method to Losing Goodwill in a Few Easy Steps
Fortunately, multiple model providers are offering open weights models at significantly lower prices than closed models.
Aeolos··on Running local models is good now
It focuses on training and data provenance, rather than serving.
Aeolos··on DeepSeek V4 Pro beats GPT-5.5 Pro on precision
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.

Aeolos··on DeepSeek makes the V4 Pro price discount permanent
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.
Aeolos··on Everything in C is undefined behavior
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.

Aeolos··on Bun's experimental Rust rewrite hits 99.8% test compatibility on Linux x64 glibc
https://fishshell.com/blog/rustport/
Aeolos··on Ubuntu 26.04 Ends 46 Years of Silent sudo Passwords
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

Aeolos··on Ubuntu 26.04 Ends 46 Years of Silent sudo Passwords
It is not, from a statistical perspective.
Aeolos··on I'm just having fun
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.

Aeolos··on I failed to recreate the 1996 Space Jam website with Claude
Why is that?
Aeolos··on Google Titans architecture, helping AI have long-term memory
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.

Aeolos··on I switched from Htmx to Datastar
Yeah, but as the HTMX author said, HTMX sucks! Definitely should use Datastar!
Aeolos··on Mago: A fast PHP toolchain written in Rust
Yet they were not - why is that?
Aeolos··on Mago: A fast PHP toolchain written in Rust
How do you deal with slow compilation times?
Aeolos··on OpenAI Progress
> 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/

Aeolos··on The borrowchecker is what I like the least about Rust
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."

Aeolos··on I am not a supplier (2022)
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.

Aeolos··on Magistral — the first reasoning model by Mistral AI
It's about as useful as your complaining.

Good riddance for Lightning.

Aeolos··on OpenAI slams court order to save all ChatGPT logs, including deleted chats
And just like that, OpenAI got banned in my company today.

Good job.

Aeolos··on Reinvent the Wheel
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.

Aeolos··on We fell out of love with Next.js and back in love with Ruby on Rails
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.

Aeolos··on Jagged AGI: o3, Gemini 2.5, and everything after
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.

← PreviousPage 2 of 12Next →