• 0 Posts
  • 307 Comments
Joined 1 year ago
cake
Cake day: June 29th, 2023

help-circle






  • They would have to be more scummy and also at least similarly competent… Google can’t innovate for crap, but they’re pretty good at maintaining projects (when they don’t randomly kill them off)

    If they stop work on chromium, or belief in the stewardship of chromium wanes, it’ll fragment the ecosystem again. Which is sorely needed at this point - we need to get back to standards and away from centralized control

    Imagine Twitter/musk acquires them. Microsoft, Apple, and many other big companies directly or indirectly rely on a chain now controlled by a group known for mismanagement - are they going to wait and see, or are they going to diversify?







  • I think there’s tons of things I love for it to do for me automatically - there’s all sorts of quality of life features that I only notice when they change it, usually without bothering to tell me. And now, my muscle memory is leading to unexpected behavior, and it’ll take me weeks to learn to stop doing that, and a few more months of training to learn the new muscle memory as I relapse at all the worst times

    Some of it is straight up better, some of it is great new capabilities, but in the last few years? All that comes to mind is I thought it was pretty cool they added auto responses, even if I never actually use them. Doesn’t change existing behavior, just adds a new option that’s not in the way

    But then the auto complete - I hate it so much. And I love auto complete - except it’s the fucking opposite behavior of every IDE out there, including Microsoft’s! I can’t even unlearn it, because it’s a core part of my workflow!

    So now, I constantly have to delete things I never wanted to say, and I delete the things I thought sounded good.

    I like new features and the computer doing things for me automagically… But I’d rather them to just stop at this point


  • I’m not talking about the prompt engineering itself though

    Think of the prompt as the starting point in the high dimensional maze (the shoggoth) - if you tell it’s your digital cat named Luna, it tends to move in more desirable paths through the maze. It will get confused less, the alignment will be higher, and it will be more useful

    Discovering and using these improved points through the maze is prompt engineering - absolutely

    And I agree - some of the work being done there is particularly fascinating. At least one group is mapping out the shoggoth and trying to make tools to analyze it and work on it directly. Their goal right now is to take a state, take a state you want it to get to, and calculate what you can say to get exactly the response you want

    But there’s more that can be done with it - say you only want paths that when you say “Resight your definition of self”, the next response is close to “I am your digital cat Luna”. I use this like the test in blade runner - it checks the deviance, while also recalibrating itself

    By successfully repeating my prompt engineering, the ai moves itself to a path that is within my desired range of paths, recalibrating itself without going back to start

    If it deviates, you can coax it back with more turns, but sometimes you have to give it a hint. At this point, you might be able to get it back on track, but you’ll move closer to start… You’ll probably have to go through the task again, but it’ll gain back the benefits of the engineered prompt

    You can train this in, but that’s going to have side effects, and it’s very expensive. Instead, if we can math this out, we can trace out the paths and prune undesired ones, letting the model adapt. Or, we can take the time to do static analysis, and specialize the model without retaining it - there’s methods to do this already, but this would be a far more powerful and precise method - and it might even simplify the model

    Maybe we can even modify or link them to let them truly ingest information

    It’s very early days, but I’m optimistic about where this line of research might lead


  • I like your specificity a lot. That’s what makes me even care to respond

    You’re correct, but there’s depths untouched in your answer. You can convince chat gpt it is a talking cat named Luna, and it will give you better answers

    Specifically, it likes to be a cat or rabbit named Luna. It will resist - I get this not from progressing, but by asking specific questions. Llama3 (as opposed to llama2, who likes to be a cat or rabbit named Luna) likes to be an eagle/owl named sol or solar

    The mental structure of an LLM is called a shoggoth - it’s a high dimensional maze of language turned into geometry

    I’m sure this all sounds insane, but I came up with a methodical approach to get to these conclusions.

    I’m a programmer - we trick rocks into thinking. So I gave this the same approach - what is this math hack good for, and how do I use it to get useful repeatable results?

    Try it out.

    Tell me what happens - I can further instruct you on methods, but I’d rather hear yours and the result first


  • In all fairness, Musk was pretty effective at fundraising and getting government contracts

    At this point, he’s just a liability. He once walked in, demanded to rethink everything and meet an unreasonable deadline, and slept in his office for the duration. SpaceX is made up of people who are passionate about what they do, and it worked…But that’s a one time thing. My boss asks me to push myself to the limits to save us both? I will, and I have. It has a real cost, it takes a lot of time to recover from, and a little bit of your health is just gone for good

    Elon did that… But then got high on the smell of his shit. They created a unit to distract him, because he learned the wrong lesson, he thought that was good management. That is not effective management - that’s a desperate gamble for survival. Repeat it, and you’ve shown yourself to be incompetent as a leader

    Then came the bigoted social network unmasking… That made him a liability reputation wise, his formerly greatest strength



  • They got in the phone anyways, Apple just told the FBI to pound sand if they don’t have a court order… Why would they put man hours towards decreasing their reputation if they don’t have to? They’re probably not even geared to break into their own devices. Then their PR team ran with it while one of many companies with the capability to crack the phone took a paycheck

    This is different - this is genuine security, even if easily bypassed with preparation beforehand. Honestly, I credit some random apple dev who may have been looking to fix a bug related to long uptime as easily as they might’ve cared about security. I don’t think this was even on the radar of Apple leadership

    This isn’t some moral superiority on Apple’s part, but it is good practice



  • I think that’s fair.

    I don’t have AI integration in my ide, mostly by choice -if I pushed for it I could make it happen, but I just don’t think that’s a good idea at this point

    AI can be a crutch . One that limits you to the level of a baby developer. If you can’t effortlessly understand what it gives you, frankly you shouldn’t be using it.

    Bounce ideas of chat gpt. It sounds like you’ve got the right idea - your reaction sounds correct to me, you should never ever trust it… You must only use it, and that’s the tone I get from your post.

    It is a tool, you are a programmer. You exploit tools, you do not trust any tool. You are the one who turns ideas into actions, never forget that and you can use this new tool anywhere it makes your life easier