vrotaru · HackerTrans

vor 4 Tagendiscuss

Just curious, can prefill be run on a machine with a mighty GPU and decode on Big Unified Memory Box?

If the prefill produces results the size of several GBs, that is probably not realistic.

vrotaru

vor 9 Monatendiscuss

Here is my experience.

Claude did generated a rather good template for what I needed. It did not compile at first but I copy-pasted the errors and it fixed them.

Not all was good, though. It used literal bullets instead of `-` required for lists, but on whole the experience was positive.

It had taken me less time to fix the template than it would been taken to write it from scratch.

Something which Claude was good at. I throw him a crude ASCII "art" representation of what I want and get the right Typst code back.

vrotaru

vor 10 Monatendiscuss

Sorry for harping on it, but I think this clearly reflects the difference between 2 approaches to storing knowledge, lossy but humongous, and lossless but limited.

LLMs - Lossy highly compressed knowledge which when prompted "hallucinates" facts. LLMs hallucinations are simply how the stored information is retrieved.

Memory (human in this case) - Extremely limited, but almost always correct.

Just an observation. No morals.

vrotaru

vor 10 Monatendiscuss

There is a podman-compose which works almost as drop-in replacement.

Almost because most common commands work, but I have not check all.

And almost, because for some docker-compose.yaml which you downloaded/LLM generated you may need to prepend `docker.io/` to the image name

vrotaru

vor 11 Monatendiscuss

That is a good questions and I guess we have good progress since Plato whose definition was - A man is a featherless biped.

But I think we still do not know.

vrotaru

vor 11 Monatendiscuss

To some degree *all* LLM's answers are made up facts. For stuff that is abundantly present in training data those are almost always correct. For topics which are not common knowledge (allow for a great variability) you should always check.

I've started to think of LLM's as a form lossy compression of available knowledge which when prompted produces "facts".

vrotaru

vor 12 Monatendiscuss

Well, not exactly convince. I was curious what will happen.

If you are curious it was a question about the behavior of Kafka producer interceptors when an exception is thrown.

But I agree that it is hard to resist the temptation to treat LLM's as a pear.

vrotaru

vor 12 Monatendiscuss

You should always check. I've seen LLM's being wrong (and obstinate) on topics which are one step separated from common knowledge.

I had to post the source code to win the dispute, so to speak.

vrotaru

vor 12 Monatendiscuss

So what is your pick?

* AI is the next electric screwdriver * AI is THE steam engine.

My pick is that the AI is not THE steam engine.

vrotaru

letztes Jahrdiscuss

> Oberon also doesn't seem to be actively developed anymore

That's pretty much it, for maybe 10+ years now. There was a successor project BlueBottle with some promise, but it did not deliver. Later it was renamed to A2. Surprisingly, it did not help.

https://en.wikipedia.org/wiki/A2_(operating_system)

IMO the authors of BB/A2 bet heavily on XML/Java hype, and were trying to make Oberon more like Java. The result was something without much internal consistency and not very usable.

Not being able to use a major browser and not having the resources to write one from scratch did not help either.

Then some of the major figures of this project left. And that was it.

There are some hobbyists and some small businesses which use it for niche projects and that is all

vrotaru

letztes Jahrdiscuss

It happens. It shows you the right suggestion, and if you keep typing it assumes that you meant something else and displays other suggestion.

Good for slow typers, not so much for quick ones.

vrotaru

vor 4 Jahrendiscuss

The web based reader will refuse to display some books, unfortunately.

In my case this was the sort of book than can be only realistically read on a big screen tablet, not on a Kindle.

Well, I've shrugged and downloaded the pdf from libgen

vrotaru

vor 4 Jahrendiscuss

Even for something which is well defined up-front this can of dubious value. Converting an positive integer less than 3000 is well-defined task. Now if you try to write such a program using TDD what do you think will end up with?

Try it. Write a test for 1, and an implementation which passes that test then for 2, and so on.

Bellow is something written without any TDD (in Java)

    private static String convert(int digit, String one, String half, String ten)     {
    switch(digit) {
    case 0: return "";
    case 1: return one;
    case 2: return one + one;
    case 3: return one + one + one;
    case 4: return one + half;
    case 5: return half;
    case 6: return half + one;
    case 7: return half + one + one;
    case 8: return half + one + one + one;
    case 9: return one + ten;
    default:
    throw new IllegalArgumentException("Digit out of range 0-9: " + digit);
    }
    }

    public static String convert(int n) {
    if (n > 3000) {
    throw new IllegalArgumentException("Number out of range 0-3000: " + n);
    }

    return convert(n / 1000, "M", "", "") + 
        convert((n / 100) % 10, "C", "D", "M") +
        convert((n / 10) % 10, "X", "L", "C") +
                convert(n % 10, "I", "V", "X");
}

comments