Skip Navigation

InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)Z

zlatko

@ zlatko @programming.dev

Posts
1
Comments
71
Joined
3 yr. ago

  • Deleted

    Permanently Deleted

    Jump

  • I mean, often enough even that phone call won't help.

    But you're right, as long as everything is working normally, working on premises slows you down to do maintenance, updates etc etc. Cloud (of all kinds) takes that work away and you can work faster. And in the VC-driven daily and eternal grind, moving faster is the only thing that matters.

  • It's all hallucinations

    Jump

  • I think not many people are aware of that. No matter how well you build the systems with this type of AI, they don't yet know. Now, maybe they're useful, maybe not, but this awareness that everything is actually just made up, by statistics and such, is lacking from peoples minds.

  • What would you do with hardware like this?

    Jump

  • No, I meant the "Anna's archive" bit, and "seed for 2.1+ ratio" and turn it off and on again - what's that about?

    (sorry for ressurecting the thread, not used to checking notifications here)

  • I've been playing an MMO that you can only play via rest API calls: Artifacts

    Jump

  • You ever got anything so good you could publish?

  • I've been playing an MMO that you can only play via rest API calls: Artifacts

    Jump

  • What would you do with hardware like this?

    Jump

  • Sounds like there's a story behind this, where could I read more?

  • Guide to software developer job advertisements

    Jump

  • Yes but if they do find a poor shmuck that wants the job, they can hope he'll undervalue himself and ask for even less.

  • Is this massive difference to be expected?

    Jump

  • yeah, traceroute might hint at that, if this is what is going on.

  • Google’s ‘Secret’ Update Scans All Your Photos

    Jump

  • I will perhaps be nitpicking, but... not exactly, not always. People get their shit hacked all the time due to poor practices. And then those hacked things can send emails and texts and other spam all they want, and it'll not be forged headers, so you still need spam filtering.

  • What's next? Picoservices?

    Jump

  • left-pad as a service.

  • What's next? Picoservices?

    Jump

  • It's probably AI-supported slop.

  • What's next? Picoservices?

    Jump

  • (Not to be confused with our premium product, ParticleServices, which just shoot neutrinos around one by one.)

  • Tradeoffs

    Jump

  • No, it's just that it doesn't know if it's right or wrong.

    How "AI" learns is they go through a text - say blog post - and turn it all into numbers. E.g. word "blog" is 5383825526283. Word "post" is 5611004646463. Over huge amount of texts, a pattern is emerging that the second number is almost always following the first number. Basically statistics. And it does that for all the words and word combinations it found - immense amount of text are needed to find all those patterns. (Fun fact: That's why companies like e.g. OpenAI, which makes ChatGPT need hundreds of millions of dollars to "train the model" - they need enough computer power, storage, memory to read the whole damn internet.)

    So now how do the LLMs "understand"? They don't, it's just a bunch of numbers and statistics of which word (turned into that number, or "token" to be more precise) follows which other word.

    So now. Why do they hallucinate?

    How they get your question, how they work, is they turn over all your words in the prompt to numbers again. And then go find in their huge databases, which words are likely to follow your words.

    They add in a tiny bit of randomness, they sometimes replace a "closer" match with a synonym or a less likely match, so they even seen real.

    They add "weights" so that they would rather pick one phrase over another, or e.g. give some topics very very small likelihoods - think pornography or something. "Tweaking the model".

    But there's no knowledge as such, mostly it is statistics and dice rolling.

    So the hallucination is not "wrong", it's just statisticaly likely that the words would follow based on your words.

    Did that help?

  • What's stopping you from writing your Rust like this?

    Jump

  • You never review code when you have no time to do an actual review? Looks good to me :)

  • TIL that "nginx" is pronounced "engine-x", and not "n-jinx"

    Jump

  • Gangaacrupt?

  • TIL that "nginx" is pronounced "engine-x", and not "n-jinx"

    Jump

  • Is that pronounced as gokoze?

  • TIL ROCm stands for "Radeon [redacted] [redacted] mlatform

    Jump

  • shaking my (trademark) head?

  • How could digitial age verification be possibly implemented with privacy in mind?

    Jump

  • So, send'em a dicpic and you're in :)

  • Yes Google, 2/3 is TOTALLY the same as 1/2

    Jump

  • considering where the garbage came from, maybe we should stop shitposting :)