Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: Is anybody building an alternative transformer?

news.ycombinator.com

Post reply on HN
Print view View original

81–90 of 96 posts

Re: Ask HN: Is anybody building an alternative transformer?

#81

Post by londons_explore »

There are a bunch of promising other ways to convert AC voltages.

The main one is the observation that the transformer uses an amount of copper and steel proportional to the power transmitted but inversely proportional to the frequency of operation.

The copper and steel cost of a transformer is the main cost (multiplied by the cost of capital for the 100+ years it will operate).

So if you can use solid state electronics to do switching at a higher frequency (switched mode power supplies, flyback designs, etc), then you can reduce the overall cost.

Re: Ask HN: Is anybody building an alternative transformer?

#82

Post by AustinDev »

londons_explore wrote: post #81

There are a bunch of promising other ways to convert AC voltages. The main one is the observation that the transformer uses an amount of copper and steel proportional to the power transmitted but inversely proportional to the frequency of operation. The copper and steel cost of a transformer is the main cost (multiplied by the cost of capital for the 100+ years it will operate). So if you can use solid state electron…

Is this response AI generated or are you lost?

Re: Ask HN: Is anybody building an alternative transformer?

#83

Post by mindcrime »

Xcelerate wrote: post #80
mindcrime wrote: post #58

Earlier quoted context omitted.

Well, to the extent that people equate GOFAI with purely symbolic / logic-based processing, then no, not for my money anyway. I think it's possible to construct systems that use elements of symbolic processing along with sub-symbolic approaches and get useful results. I think of it as (although this is something of an over-simplification) taking symbolic reasoning, relaxing some of the constraints that go along with…

I’ve never liked that term “sub-symbolic”. It implies that there is something at a deeper level than what a Turing machine can compute (i.e., via the manipulation of strings of symbols), and as far as we can tell, there’s no evidence for that. It might be true, but even a quantum computer can be simulated on a classical computer. And of course neural networks run on classic computers too. Yeah, I know that’s not what…

It's not the name I would have chosen either (probably) but I wasn't around when those decisions were being made and nobody asked me for my opinion. So I just roll with it. What can ya do?

Re: Ask HN: Is anybody building an alternative transformer?

#84

Post by lurquer »

AustinDev wrote: post #82
londons_explore wrote: post #81

There are a bunch of promising other ways to convert AC voltages. The main one is the observation that the transformer uses an amount of copper and steel proportional to the power transmitted but inversely proportional to the frequency of operation. The copper and steel cost of a transformer is the main cost (multiplied by the cost of capital for the 100+ years it will operate). So if you can use solid state electron…

Is this response AI generated or are you lost?

There are several Transformers successors and spinoffs across various media. Animated series like Beast Wars: Transformers (1996) introduced a new generation of transforming robots, shifting from vehicles to animals. Later, Transformers: Prime (2010) and Transformers: Cyberverse (2018) continued evolving the story and animation style. The live-action film series, starting in 2007, led to spinoffs like Bumblebee (2018) and an expanding cinematic universe. Beyond official media, franchises like Go-Bots (a competitor turned subsidiary) and Voltron (though distinct, often compared) reflect Transformers’ legacy in robot-focused storytelling.

Re: Ask HN: Is anybody building an alternative transformer?

#87

Post by dr_dshiv »

Xcelerate wrote: post #80
mindcrime wrote: post #58

Earlier quoted context omitted.

Well, to the extent that people equate GOFAI with purely symbolic / logic-based processing, then no, not for my money anyway. I think it's possible to construct systems that use elements of symbolic processing along with sub-symbolic approaches and get useful results. I think of it as (although this is something of an over-simplification) taking symbolic reasoning, relaxing some of the constraints that go along with…

I’ve never liked that term “sub-symbolic”. It implies that there is something at a deeper level than what a Turing machine can compute (i.e., via the manipulation of strings of symbols), and as far as we can tell, there’s no evidence for that. It might be true, but even a quantum computer can be simulated on a classical computer. And of course neural networks run on classic computers too. Yeah, I know that’s not what…

Read Paul Smolensky’s paper on the harmonium. First restricted Boltzmann machine. The beginning helps justify subsymbolic in a pretty beautiful way.

Re: Ask HN: Is anybody building an alternative transformer?

#88

Post by singularity2001 »

Working on variants of Byte Latent Transformer [0] to get rid of tokenization which hinders mathematical performance and letter reflection.

In the original Byte Latent Transformer paper they reintroduce ugly caching and n-grams which I'm looking to eliminate.

As expected pure byte level Transformers need some rethinking to keep them performant, some kind of matryoshka mechanism so that long predictable byte sequences (words and phrases) get grouped into a single latent vector.

The idea is to apply this "Byteformer" not just on text but also on compiled files, songs etc.

If it's impossible to scale this architecture at least a modified tokenizer could be helpful which falls back to bytes / unicode once a number or an unfamiliar word is encountered.

[0] https://arxiv.org/abs/2412.09871

Re: Ask HN: Is anybody building an alternative transformer?

#89

Post by Xcelerate »

mindcrime wrote: post #83
Xcelerate wrote: post #80

Earlier quoted context omitted.

I’ve never liked that term “sub-symbolic”. It implies that there is something at a deeper level than what a Turing machine can compute (i.e., via the manipulation of strings of symbols), and as far as we can tell, there’s no evidence for that. It might be true, but even a quantum computer can be simulated on a classical computer. And of course neural networks run on classic computers too. Yeah, I know that’s not what…

It's not the name I would have chosen either (probably) but I wasn't around when those decisions were being made and nobody asked me for my opinion. So I just roll with it. What can ya do?

Oh for sure! Wasn’t critiquing your comment at all. I’ve seen the term a lot lately and it just made me wonder how much the industry is using it as a misleading hype factor. E.g., LLMs are “better” than Turing machines because they are operating at a level “below” Turing machines even though the comparison doesn’t make sense, as symbolic computation isn’t referring to the symbol-manipulating nature of Turing machines in the first place.
Post reply on HN