• 7 Posts
  • 44 Comments
Joined 2 years ago
cake
Cake day: July 1st, 2024

help-circle
  • Personally I still have a soft spot for Newsboys. Mostly just Shine, and Take Me To Your Leader. Those two still feel good.

    Initially I kinda liked Audio Adrenaline, but looking back with what we all know now about the impact of a car based society on the world, I gotta admit, “Chevette” didn’t have an ounce of gospel in it, and was a much worse take on crappy cars that probably leaked toxic trash everywhere they went than Adam Sandler’s “Ode to my Car”.




  • Of course it sounds out of touch. I didn’t say it, or anything like it. Just like the other commenter, you seem to have stopped after the first sentence.

    20 years of IT experience from a support perspective does qualify me to put anybody in the programming space on notice. The tools might not be as good as a talented and well trained dev, but they’re already better than a lazy dev. The output I get from Claude Code takes effort to get running. It just takes less of it than the output from my outsourced offshore MSP.



  • I’m building my own set of libraries regarding things I’ve had to fix in Claude’s output across multiple similar requests. So far it does seem to be helping. I’m sure the next iteration of the product will incorpororate all manner of innovations stemming from ways users have interacted with it at the free tier, and perhaps the rest of its interactions as well depending on whether they find a way to legally meet their definition of privacy while somehow keeping the code portion of the learnings.

    When the version of Sonnet, Haiku, and Opus ticks up to a number higher than 4.6, I wouldn’t be surprised if it clears some substantial “first draft usable” hurdles for small data acquisition, transform, and analysis level programming.

    I’m focused on the IT administration space, so most of my dev needs are predictable. This just lets me interact with Microsoft’s various REST APIs in a much more direct fashion than their own administration websites. In regards to that space I’m pretty much ready to share a set of libraries with the other folks on my team. With any luck, they’ll be able to use these libraries to catch most of the mistakes Claude likes to make getting data from Microsoft sources, with documented functional paths past the major sticking points.


  • I’ve never been able to program in anything more complex than BASIC and command line batch files, but I’m able to get useful output from Claude.

    I’m an IT Infrastructure Manager by trade, and I got there through 20 years of supporting everything from desktop to datacenter including weird use cases like controlling systems in a research lab. On top of that, I’ve gotten under the hood of software in the form of running game servers in my spare time.

    What you need to get good programs out of AI boils down to 3 things:

    1. The ability to teach an entity whose mistakes resemble those of a gifted child where it went wrong a step or ten back from where it’s currently looking.
    2. The ability to provide useful beta test / debug output regarding programs which aren’t behaving as expected. This does include looking at an error log and having some idea what that error means.
    3. Comfort using (either executing or compiling depending on the language) source code associated with the language you’re doing things in. This might be as simple as “How do I run a Powershell script or verify that I meet the version and module requirements for the script in question?”, or it might be as complicated as building an executable in Visual Studio. Either way whatever the pipeline is from source to execution, it must be a pipeline you’re comfortable working with. If you’re doing things anywhere outside the IT administration space, it’s reasonable to be looking at Python as the best first path rather than Powershell. Personally, I must go where supported first party modules exist for the types of work I’m developing around. In IT Administration, that’s Powershell.

    I’ve made tools which automate and improve my entire department’s approach to user data, device data, application inventory, patch management, vulnerability management, and these are changes I started making with a free product three months ago, and two months back I switched to the paid version.

    Programming is sort of like conversation in an alien language. For that reason, if you can give precise instructions sometimes you really can pull something new into existence using LLM coding. It’s the same reason that you could say words which have never been said in that specific order before, and have an LLM translate them to Portuguese.

    I always used to talk about how everything in a computer was math, and that what interested me more than quantum computing would be a machine which starts performing the same sorts of operations on words or concepts that computers of that day ('90s and '00s when “quantum” was being slapped on everything to mean “fast” or “powerful”) were doing on math. I said that the best indicator when linguistic computing arrives would be that without ever learning to program, I’d start being able to program. I was looking at “Dragon Naturally Speaking” when I had this idea. It was one of the earliest effective speech to text programs. I stopped learning to program immediately and focused exclusively on learning operations from that point forward.

    I’ve been testing the code generation abilities of LLMs for about three years. Within the last six months I feel like I’m starting to see evidence that the associations being made internally by LLMs are complex enough to begin considering them the fulfillment of my childhood dream of a “word computer”.

    All the shitty stuff about environment and theft of art is all there too, which sucks, but more because our economic model sucks than because LLMs either do or do not suck. If we had a framework for meeting everybody’s basic needs, this software in its current state has the potential to turn everyone with a passion for grammatical and technical precision into a concept based developer practically overnight.



  • The words are all still stupid because it’s a new thing, but there is one specific space that I find it just impossible to deny the way that there are already tools on the market that change the way the job is done:

    Claude can turn plain english statements about what data I want from what different parts of the Microsoft 365 administration ecosphere into scripts that take all that data, transform it the way I want it transformed, and turn it into spreadsheets, pivot tables, data manipulation macros, and everything else I need to answer questions which are really hard to answer from the MS web interface. I can ask things like “Which systems have any of these three known vulnerable apps?” or “What software is common to everyone working in this division of the company?”

    It’s boring stuff, but it makes a world of difference in terms of what I can look at to base my decisions on. I spent less time building repeatable reports for each type of object I need to think about (device, application, user) than I did building even one report for one assessment in years past without automation. And it’s not constantly asking the LLM to do things for me, it’s building a couple of tools with a much faster iterative process for feature tweaks or debugging than could take place as an interaction between two people. I was making changes to scripts

    I’m using it only for specific work areas where I already know the APIs I just don’t have the time to stumble through the gather and collate of the various data. Based on the level of complexity of the tools I’ve been able to build I would say that anybody who knows how to describe the data they work with most could use a tool like this to make that process a lot more automatic. We’re not ready for the tool to do the work without human oversight, but we’re ready for anybody who works with stacks of data to build their own automation instead of having it built for them.


  • The modern left has a different “no matter who”, I think. Currently my favorite expression of the thing comes from Dan Soder’s podcast. I’m paraphrasing quite a bit here, but gist is that professional baseball and football have been proving for decades that you gotta have salary caps or the whole sport goes to shit. The people who have been the most disenfranchised for the longest currently aren’t ready to hear what you have to say unless you’re willing to start talking about “salary capping” billionaires so that you don’t end up with all kinds of secret monstrous child sex abuse stuff on plantations all across the world in days on by as well as pretty recent memory. and islands both in the news and assumably other places even to this very day. What we’re doing isn’t working. The money’s all made up anyway. We gotta rearrange the money in a manner that’s gonna fix rich people’s ability to hide entire islands of depravity, and while we’re at it cause a little bit less war and less making people hustle so extra hard for such a large portion of their life, to the detriment of their health, their inner peace, and their ability to find a personally fulfilling way to contribute meaningfully to the betterment of others. Most of us want to be nice to each other. We’re mad about how far off the mark everything is.

    This sort of person would never take Newsom, because someone who gets their photo taken clearing out a homeless camp is utterly incapable of being “the guy” about any of the stuff that matters. He doesn’t see the depravity of it, the abomination which brings desolation…





  • quixote84@midwest.socialOPto196@lemmy.blahaj.zonean old rule
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    In this specific case, the knowledge regarding how to build a house is easier to acquire than the knowledge regarding the delicate balance of the ecosystem which used to thrive where you built your house.

    Some knowledge is easier to acquire than other knowledge, and that inequity breaks things that only get figured out generations or centuries down the line.


  • I’m of the opinion that the top half is almost as bad.

    We are ruled by very old dragons, possibly even “grand” dragons. What’s happening now more closely resembles removing of a mask than a complete 180 shift in policy.

    It’s still something which deserves to be opposed as strongly as possible. It’s just… the honest character of a nation founded on breaking every promise it ever made to the original occupants of this land, fighting a war with itself over the right to own people, joining the colonial game within four years of “the frontier” being closed, refusing to ratify the Treaty of Versailles, bombing Laos and Cambodia just because they’re in close proximity to a nation which was the current target of our 75+ year endless war, and violating international treaties regarding ethical treatment of political prisoners in the manner seen in Abu Ghraib or with the “enhanced interrogation” which took place in Gitmo.

    This is the bad place.




  • Since this place has midwest in the name, and the main mod is from Ohio, I’m gonna roll some dice here. If you happen to be anywhere near northeast Ohio, There’s a group in Cuyahoga Falls called “Meaningful Conversations Akron” that can be found on FB and meets every Saturday morning at 9:30 AM. They leverage principles of interfaith spirituality to stay focused on the sort of unity which is necessary as a goal in order to even begin winding down the division that dragged us here.

    The old stickied post suggested going out and making friends in person. That effort is how I found that group. It’s been really good for me.


  • In the immediate future, the screenshot archive becomes unmanageable.

    In the long term future, it becomes the modern equivalent of what your parents and grandparents got out of keeping a scrapbook or photo album.

    I’ve been chronically online since 1997. Going through a scrap folder which I held onto when decommissioning an old PC or phone brings back all kinds of memories. I even find that noting the changes in my meme taste can be really useful for identifying points where I’ve grown as a person. That, in turn, leads to reprocessing old memories and identifying ways in which I brought something to the table which facilitated some of my own bad experiences. That helps me heal.