Hugsun · HackerTrans

il y a 8 joursdiscuss

That can only be true if the workload is compute bound, not memory bandwidth bound.

il y a 12 joursdiscuss

Iceland has mostly been governed by the center right conservative independence party, which has been quick to sell land and resources to anyone interested. Kárahnjúkar is the canonical example of this, a huge hydro plant powering aluminium smelters owned by a foreign company.

Right now, different parties have the majority rule, and their interest in projects like these are not clear. I would suspect that a motivated investor could fairly easily get them built. The hurdles would be logistics and connectivity much more than red tape.

Iceland is culturally and politically scandinavian with some influence from the US. In august there will be a vote to start accession talks with the EU. This has been a heavily contested issue for years, largely due to Iceland's unique resources.

Hugsun

le mois dernierdiscuss

Is there anything of value in this project?

It sounds interesting at a glance, but it seems to be AI slop. So it's hard to tell if there are any interesting discoveries there, or just some worthless results described with performatively advanced language.

Hugsun

le mois dernierdiscuss

Have you tried Qwen 3.6 or Gemma 4? They're not frontier level but certainly have their uses.

Hugsun

il y a 2 moisdiscuss

Note that your monitor is a QD-OLED, not a QLED monitor.

Despite the similar names, these are two very different technologies. QD-OLED is a OLED panel that uses QD (quantum dots) to achieve a wide color gamut. QLED is a LED backlit LCD panel that uses QD in a similar way.

The difference in performance characteristics of these two panel types is dominated by the difference between OLED and LCD.

Hugsun

il y a 2 moisdiscuss

That HN agent review is pretty usable. Very cool!

Hugsun

il y a 2 moisdiscuss

It is unbelievable that this is a controversial opinion.

Hugsun

il y a 2 moisdiscuss

That seems like a decently sized market. Maybe not for an AI lab though.

Hugsun

il y a 2 moisdiscuss

Two things can be true at once.

Hugsun

il y a 3 moisdiscuss

The whole post and that paragraph in particular sound AI generated, that triple "No" is a big tell. I'd not be surprised if that confirmation complaint is just a random suggestion proposed by the AI that wrote this.

Hugsun

il y a 3 moisdiscuss

They're comparing Qwen's moe vs dense (smaller difference) against Gemma's moe vs dense (bigger difference). Your proposed alternative misses the point.

Hugsun

il y a 3 moisdiscuss

Unfortunately, llama.cpp quantization technology has been stagnant for two years. The main quantization developer left or was kicked out of llama.cpp due to an attribution dispute. He created his own fork ik_llama.cpp where he has made multiple new and better quants.

unsloth and byteshape are just using and highlighting features that have been available the whole time. I am very invested in figuring out a solution to this dispute, or some way to get the new quants upstreamed.

Hugsun

il y a 4 moisdiscuss

LLMs produce a distribution of token probabilities which is then sampled. This sampling is the only random part of the system.

If you just take the most probable token every time, the system becomes fully deterministic. We don't do this as the output becomes more stiff and less creative.

Hugsun

il y a 5 moisdiscuss

SCOTUS is indeed compromised.

Hugsun

il y a 7 moisdiscuss

I heard from a medium reliable source that this loophole wasn't as popular as the zeitgeist implies. I'd love to know how true that is and if so, how the rich finance themselves.

Hugsun

il y a 8 moisdiscuss

I listened to a few episodes on a recommendation. The episodes lead you to believe that the host is some agnostic person that's just curious about these reports. They are not as the original lead is from another superstition believer podcast.

They also present the cameraman as a token skeptic, who is of course quickly swayed into belief.

They lean heavily on a host of tricks with long histories of non-reproduction when tested rigorously.

A "scientist" (known crackpot and woo believer) is employed to make the experiments sound. And their terrible academic reputation was explained away using conspiratorial arguments.

I found TT wholly unconvincing and consider it a scam to get people to pay for the actual evidence. I won't pay of course and confidently assume it to be poor based on the publicly available material.

Hugsun

il y a 10 moisdiscuss

I've found GPT-5 Thinking to perform worse than o3 did in tasks of a similar nature. It makes more bad assumptions that de-rail the train of thought.

Hugsun

l’année dernièrediscuss

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

l’année dernièrediscuss

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.

comments