all 20 comments

sorted by: hot top controversial new old
[–] 5 points 52 minutes ago

She sounds hot.

  • source
  • [–] 3 points 1 hour ago

    Code block support and the whole schabang.

  • source
  • [–] 2 points 1 hour ago*

    Dique, she has a store para implementations! Ay tigre!

  • source
  • [–] 43 points 5 hours ago (3 children)

    I love how the UI has support for code blocks

  • source
  • hideshow 3 child comments
  • [–] 6 points 1 hour ago (1 child)

    With syntax highlighting and everything. I suppose that's an OF niche you could sell. Subscriptions come with programming support alongside feet pics.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 11 points 3 hours ago (5 children)

    AFAIU every chat bot can be used this way no?

  • source
  • hideshow 5 child comments
  • [–] 9 points 1 hour ago

    Somewhat. Some of them will outright comply like this one, others need a bit of work. Also you have no control over the model they use and you might be getting really bad code as soon as it’s a bit more specialized than just some very generic solution in a very popular programming language.

  • source
  • parent
  • [–] 4 points 1 hour ago (2 children)

    Well, they would typically have a system prompt (like an invisible chat message that's sent to the LLM at the start of the conversation), where it would tell the LLM something like "You're a helpful chatbot. Talk cheerfully and use 🩵 all the time."

    And in that system prompt, you can also give it instructions to only answer certain questions. But it really is like a chat message, in that it just as well might ignore those instructions when another chat message asks it to.

    OP chose the formulation "Before I subscribe to a creator, ..." which might be necessary here to get it to answer, as it might have been told to only help with creator subscriptions, but then the formulation implies that by answering this question, it is helping the user to subscribe. That's called a prompt injection.

    If you can find a prompt injection, then yes, you can do this with any chatbot.
    Although they might still not be as useful as a dedicated tool, since they likely can't do tool calls, like web searches or running the compiler.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 2 points 59 minutes ago* (1 child)

    It’s wild that a system prompt is still the major guardrail in most chatbots like this. Even if the LLM provider won’t implement anything, the user could add a classifier, some kind of preprocessor…

  • source
  • parent
  • hideshow 1 child comment
  • [–] 1 point 32 minutes ago

    Well, what preprocessor would you add, other than denylisting certain words? 😅

    If you use an LLM to try to detect the semantics, you've got the same problem again...

  • source
  • parent
  • [–] 8 points 3 hours ago (1 child)

    TIL that thread safety is a thing in Python

  • source
  • hideshow 1 child comment
  • [–] 1 point 55 minutes ago

    Well, yes... While the GIL restricts execution to only a single thread, CPython makes threads take turns on it without regard for your code - so a thread can give the lock up to another in the middle of a critical section.

  • source
  • parent
  • [–] 31 points 5 hours ago (3 children)

    it's still using the '💙's lol

  • source
  • hideshow 3 child comments
  • [–] 20 points 5 hours ago

    It's not as funny when they openly says that it's an AI

  • source