HNHacker News
TopNewBestAskShowJobs

Hugsun

717 karma · joined June 9, 2021

https://arnaldur.be
submissionscomments
Hugsun··on Ollama violating llama.cpp license for over a year
Consensus seems to be forming around the fact that Ollama is not genuinely trying to be part of the open-source community.
Hugsun··on Ollama's new engine for multimodal models
Ollama are known for their lack of transparency, poor attribution and anti-user decisions.

I was surprised to see the amount of attribution in this post. They've been catching quite a bit of flack for this so they might be adjusting.

Hugsun··on Gemini 2.5 Flash
I've experienced this a lot as well. I also just yesterday had an interesting argument with claude.

It put an expensive API call inside a useEffect hook. I wanted the call elsewhere and it fought me on it pretty aggressively. Instead of removing the call, it started changing comments and function names to say that the call was just loading already fetched data from a cache (which was not true). I could not find a way to tell it to remove that API call from the useEffect hook, It just wrote more and more motivated excuses in the surrounding comments. It would have been very funny if it weren't so expensive.

Hugsun··on AI 2027
I have not yet found any compelling evidence that suggests that there are limits to the maximum intelligence of a next token predictor.

Models can be trained to generate tokens with many different meanings, including visual, auditory, textual, and locomotive. Those alone seem sufficient to emulate a human to me.

It would certainly be cool to integrate some subsystems like a symbolic reasoner or calculator or something, but the bitter lesson tells us that we'd be better off just waiting for advancements in computing power.

Hugsun··on Qwen2.5-VL-32B: Smarter and Lighter
How are you using them? Who is enforcing the daily quota?
Hugsun··on OpenAI's o1-pro now available via API
How long is it's thinking time when compared to o1?

The naming would suggest that o1-pro is just o1 with more time to reason. The API pricing makes that less obvious. Are they charging for the thinking tokens? If so, why is it so much more expensive if there are just more thinking tokens anyways?

Hugsun··on Deep Learning Is Not So Mysterious or Different
Really!? Do you have a source for this? This would be really interesting if true.
Hugsun··on High-Speed Face-Tracking for Dynamic Facial Projection Mapping
What sort of propaganda do you forsee this enabling?
Hugsun··on DeepSeek-R1
I wrote an article about the reasoning abilities of LLMs some time ago. During it's creation I discovered that ChatGPT failed this simple /test/ https://www.arnaldur.be/writing/about/large-language-model-r...

One of the DeepSeek-R1 models solve it, but it's a pretty funny solution:

``` User: A man and a goat are on one side of a river. They want to cross it. They have a boat. What steps do they need to follow?

DeepSeek-R1-Distill-Qwen-32B: <think> Okay, so there's this puzzle where a man and a goat are on one side of a river, and they want to cross it using a boat. Hmm, let's see. I remember hearing similar problems before, usually involving other animals or objects, like a wolf and a cabbage, or something like that. Those often require some strategic thinking about what can be left alone and what needs to be taken first.

In this case, though, it's just a man and a goat. That seems simpler, but maybe there's a catch I'm not seeing. Let me think step by step. So, the man needs to get the goat across the river. The boat is there, so they can use that. But is there anything else involved? I mean, sometimes in these puzzles, you have other elements that complicate things, like a wolf or something else that can't be left alone with the goat. But here, it's only the man and the goat.

Wait, perhaps the simplicity is the key. Maybe the answer is straightforward because there's only two things involved—the man and the goat. So, the steps would be something like: the man takes the goat into the boat, rows across, and then they're both on the other side. That seems too easy, but maybe that's it. I mean, when you have more items, you have to be careful about leaving certain things alone, but here, since it's just the man and the goat, there's no risk of anything getting into trouble if left alone.

But maybe I'm missing something. Let me visualize it. The man is on one side, the goat is with him. He gets into the boat, takes the goat with him, rows across the river, and then they're both on the other side. There's no mention of anything else he needs to bring back or anything else on the other side. So, maybe the solution is just that simple.

Alternatively, sometimes in these puzzles, the boat can only carry one or two, but in this case, since it's the man and the goat, maybe the boat can hold both. I think the key here is that there are no other animals or items to worry about, so the steps are straightforward.

Wait, but in the traditional puzzle, the man has to take items across, and sometimes has to make multiple trips because he can't leave certain things unattended. But since here it's only the man and the goat, maybe the problem is designed to test if the person recognizes that the only complication (like in the classic puzzle with another animal) isn't present here, so the steps are much simpler.

So, to break it down:

    Man and goat are on the starting side.
    Man gets into the boat with the goat.
    Man rows the boat to the other side.
    They both arrive safely on the other side.
That seems to be it. There's no complication, so the solution is straightforward. I think I might be overcomplicating it, but considering the problem only mentions the man and the goat, there's nothing else to juggle. So, the steps are just taking both across in one trip.

Yeah, I think that's it. No need to worry about leaving the goat alone because there's nothing else to cause a problem. So, the answer is simple in this case. </think>

The man and the goat can cross the river in one smooth trip since there are no other elements to complicate the process. Here's how they do it:

    Board the Boat: The man gets into the boat with the goat.
    Row Across the River: The man rows the boat to the opposite side.
    Arrive Safely: Both the man and the goat safely reach the other side.
This straightforward approach works because there are no additional constraints or elements to consider. ```

I'm curious to know if there is a good reason for this very rambly style of speech.

Hugsun··on Apache DataFusion
How do you infer your Parquet schemas?
Hugsun··on GPT-5 is behind schedule
I mostly feel sorry for grandpa, he'll receive much less of these questions, if any. This is partially because I expect to become this grandpa and already suspect that some people aren't asking me questions they would be, if they had no access to chatgpt.
Hugsun··on GPT-5 is behind schedule
I think it's good of you to make them critically engage with the subject by verbalizing it themselves. Evidence suggests that video consumption is relatively un-engaging mentally, likely as it demands nothing of you.
Hugsun··on Show HN: Lfi – a lazy functional sync, async, and concurrent iteration library
How does this compare to Effect, or Fluture? There have been so many attempts at improving these things in JS that it's hard to keep track.
Hugsun··on Watermark Anything
Note that stenography is very different from steganography.

https://en.wikipedia.org/wiki/Stenography

https://en.wikipedia.org/wiki/Steganography

Hugsun··on How 'Factorio' seduced Silicon Valley and me
Consider yourself lucky. I enjoy programming in itself greatly, but I don't find myself motivated by producing anything useful.
Hugsun··on X isn't important enough to feel the full force of EU regulation
His behavior, especially recent ones, has soured my view of all of his endeavors. I'm saddened by that fact.
Hugsun··on An n-ball Between n-balls
Very interesting, I've considered doing something similar with other regular polyhedra, like the n-simplex (the one you analyzed) and n-orthoplex.

What was the side length in your calculation? did you find an equation for the size of the center n-ball?

Hugsun··on Germany's 49-euro ticket resulted in significant shift from road to rail
I'd wager that those subsidies have very strong returns on investment. From a thermodynamic standpoint, trains are clearly the most efficient long distance transportation technology. The inefficiencies almost always appear as cost.
Hugsun··on Mind Wandering: More than a Bad Habit (2018) [pdf]
There are is an unfortunately large proportion of them that are fooled by the emotion and believe it.
Hugsun··on An n-ball Between n-balls
Haha, that's a really funny similarity. I appreciate you sharing it :)
Hugsun··on Germany's 49-euro ticket resulted in significant shift from road to rail
It is indeed too high. It is the price though. Put in Aarhus H and København H here: https://pendlertjek.dsb.dk/
Hugsun··on X isn't important enough to feel the full force of EU regulation
Certainly. Elon seems to be willing to go to extreme lengths to avoid regulation.
Hugsun··on Germany's 49-euro ticket resulted in significant shift from road to rail
It sounds amazing. All these prices seem crazy low. A significantly zone limited monthly commuter ticket here in Denmark costs over 500€
Hugsun··on Conway's Gradient of Life
Interesting. I can't zoom on mobile which is frustrating.
Hugsun··on An n-ball Between n-balls
> you could replace every instance of "ball" in this article with "sphere" and it would still be correct.

I completely agree. N-ball is maybe more mathematically precise. It might rule out some strange edge case I couldn't think of. I chose it mostly for stylistic reasons. n-ball is shorter than n-sphere, and ball is a more playful term.

I do however understand the need to define the two object classes, and see little issue with giving them distinct names.

Hugsun··on An n-ball Between n-balls
Yep, thanks for the great contribution!
Hugsun··on Sq.io: jq for databases and more
There's no reason not to post it.
Hugsun··on An n-ball Between n-balls
To be clear: the commenter you replied to just seems to be reiterating the idea, so I'm not accusing them of not reading the article.

You should have seen how few replies read the last article I posted. https://news.ycombinator.com/item?id=40525629 The majority of the comments, including all the top ones, expressed insights as original, that were pretty thoroughly analyzed in the article. Just read my mildly frustrated replies.

Hugsun··on An n-ball Between n-balls
That's a good point. High dimensional objects can obtain very unintuitive properties, like you describe.

This to me feels similar in many ways to how a corner in a high dimensional n-cube, although 90 degrees, no matter how you measure it, seems extremely spiky. As the shape does not increase in width, but the corners extend arbitrarily far away from the center. A property reserved for spiky things in 3D.

Hugsun··on An n-ball Between n-balls
This guy gets it!
← PreviousPage 2 of 10Next →