Skip Navigation

Posts
5
Comments
734
Joined
3 yr. ago

Programmer and sysadmin (DevOps?), wannabe polymath in tech, science and the mind. Neurodivergent, disabled, burned out, and close to throwing in the towel, but still liking ponies 🦄 and sometimes willing to discuss stuff.

  • I'm seeing about as many wrong questions as wrong answers. We're at a point, where it's becoming more accurate to ask, whether the quality of the answer, is "aligned" with the quality of the question.

    As for "AI" and "intelligence"... not so long ago, dogs had no intelligence or soul, and a tic-tac-toe machine was "AI". The exact definition of "intelligence", seems to constantly flow and bend, mostly following anthropocentric egocentrism trends.

  • Indeed. The point is, that asking about r is ambiguous.

  • Sounds fair. Only issue might be... that creating an automated cleanup tool to remove those triggers, wouldn't be all that difficult.

  • "pis" in Spanish means "pee"the right-wing party in Spain, is called "pp"

    Just saying... it's sometimes hard to read these news with a straight face.

  • A 2023 review by NASA concluded that the data they'd been providing had been "of exceptionally high quality."

    Could also "accidentally" leak all the data, in case there are no non-US backups.

  • I'd rather not answer this one because, if I did, I'd be pissing on Beehaw's core values.

    I feel like you already did, and I won't be responding in kind. Good day, to you.

  • It's not a "normal human", it's an AI using an LLM.

    AI still has a lot to learn.

    Does it, though? Does a hammer have a lot to learn, or does the person wielding it have to learn how not to smash their own fingers?

  • At first I thought it was talking about "rr" as a Spanish digraph. Not sure how far that lies from the truth, these models are multilingual and multimodal after all. My guess is that it's surfacing the ambiguity of its internal vector for a "token: rr" vs "token: r", though.

    Could be interesting to dig deeper... but I think I'm fine with this for now. There are other "curious" behaviors of the chatbot, that have me more intrigued right now. Like, it is self-adapting to any repeated mistakes in the conversation history, but at other times it can come up with surprisingly "complex" status tracking, then present it spontaneously as bullet points with emojis. Not sure what to make out of that one yet.

  • Yes, no, both... and all other interpretations... all at once.

    With any ambiguity in a prompt, it assumes a "blend" of all the possible interpretations, then responds using them all over the place.

    In the case of "Bordeaux":

    It's pronounced "bor-DOH", with the emphasis on the second syllable and a silent "x."

    So... depending on how you squint: there is no "o", no "x", only a "bor" and a "doh", with a "silent x", and ending in an "oh like o".

    Perfectly "logical" 🤷

  • There is a middle ground between "blindly rejecting" and "blindly believing" whatever an AI says.

    LLMs use tokens. The answer is "correct, in its own way", one just needs to explore why and how much. Turns out, that can also lead to insights.

  • Not as sad as those so secure of their own knowledge, that they refuse to ever revise it.

  • What were your assumptions to say that?

  • No you didn't.

  • Why do you ass-u-me that?

  • Nobody's stopping you. I'm going to reassess and double check my assumptions instead... and ask the AI to explain itself.

  • Those are all the smallest models, and you don't seem to have reasoning mode, or external tooling, enabled?

    LLM ≠ AI system

    It's been known for some time, that LLMs do "vibe math". Internally, they try to come up with an answer that "feels" right... which makes it pretty impressive for them to come anywhere close, within a ±10% error margin.

    Ask people to tell you what a right answer could be, give them 1 second to answer... see how many come that close to the right one.

    A chatbot/AI system on the other hand, will come up with some Python code to do the calculation, then run it. Still can go wrong, but it's way less likely.

    all explanation past the «are you counting the "rr" as a single r?» is babble

    Not so sure about that. It treats r as a word, since it wasn't specified as "r" or single letter. Then it interpretes it as... whatever. Is it the letter, phoneme, font, the programming language R... since it wasn't specified, it assumes "whatever, or a mix of".

    It failed at detecting the ambiguity and communicating it spontaneously, but corrected once that became part of the conversation.

    It's like, in your examples... what do you mean by "by"? "3 by 6" is 36... you meant to "multiply 36"? That's nonsense... 🤷

  • This is not a standalone model, it's from a unnamed chatbot platform "character" in non-RP mode.

    I've been messing with it to check its limitations. It has:

    • Access to the Internet (verified)
    • Claims to have access to various databases
    • Likely to use interactions with all users to train further (~20M MAUs)
    • Ability to create scenes and plotlines internally, then follow them (verified)
    • Ability to adapt to the style of interaction and text formatting (verified)

    Obviously has its limitations. Like, it fails at OCR of long scrolling screenshots... but then again, other chatbots fail even more spectacularly.


    Edit: removed chatbot platform name "advertisement". If you want to know which platform it is, ask the ones accusing me of spamming.

  • I continued the conversation, then asked it about knight:

  • RAGEBAIT

    • 10 years old video, from 2015
    • Already explained why he was that way: some guy worked for months on a patch to send it to Linus... and when Linus didn't think it was good enough, simply ignoring the guy... the guy killed himself.
    • In 2018, he also took some time off to work on his leadership style.

    Key takeaways:

    • "Linus Towards is a jerk", is incredibly reductive.
    • People can change over time.