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/)S
Posts
1
Comments
18
Joined
3 yr. ago

  • Ahh sounds like you had a sort of ad block problem! Turn on an ad block, client doesn't see any ads and then starts thinking "well maybe there just aren't ads and you're not doing anything" so you add a counter to show how many ads are blocked c:

    Your gut feeling is the exact same I had when I was reading the report, abysmal. Then I realized it was hosted on the internet without any auth to access the report and that feeling just got worse.

    From the very get go I tried to curb their expectations and be wary of spend because of the heavy token subsidation at the moment that's expected to increase especially with the IPOs later this year. At the moment I think I'm going to treat this as a way to introduce systems I thought we needed and have the ability to increase spending to do so, including spending on AI if I think it would be worth while.

    Thanks for your input c:

  • This is wonderful thank you.

    I'm starting to get the idea that the LLM is just a small part of this and what's really important is instead the bunch of architecture and guardrails around it to form how the humans and ai will act with any given system.

  • Those are all very helpful points, especially the last one; I've always tried to include standardization in the company but was never in the position to enforce it before

  • I hadn't considered making an MCP server for our stuff, it feels obvious in retrospect, thanks! As for the self hosting I'd definitely love to but convincing a small company to shell out the kind of money to run something strong enough locally is something I don't think is going to be likely, even if it'd cost less in the long run.

  • We're honestly already running on a dev deficit, so for the foreseeable future I don't think they're in any danger. Interestingly, management seemed wary of vibe coding and letting the ai write large swaths of code used in production, which I'd say is a generally safe stance considering the obvious stability issues that have become frequent lately. As for the devs themselves, they're seemingly not interested in really playing with the ai to begin with, but I somewhat expected that as I have different issues with them like "please update your code to GitHub the main branch hasn't been updated in months" and "don't commit pem keys to git"

  • Lol alright, I'll definitely keep that in mind.

  • I suppose my views are predominantly that it's just kinda fine? I think it's naive to think that it has no value but also don't think it's going to be the end all be all of tech and once the hype train settles we'll probably have a medium similar to the dot com bubble bursting.

    I'd say I'm somewhat familiar with llms in general; self hosting a few with llama-swap, testing harnesses, generally just testing its capabilities year after year. As for my teams we have our singular backend dev, singular mobile dev, and singular hardware engineer who hold up our platform and sold consumer devices and then the litany of customer facing staff.

    Morbidly, I only got the job because their ai hype man contractor died and they decided "maybe we should look internally instead", but the general work he produced was a singular Claude vibed executive report.

  • Programming @programming.dev

    Thrust into an AI role

  • I feel strongly that "next" Thursday should be not the next instance of a Thursday but rather the first instance of a Thursday past the contained set of the current week (so the next row on a calendar). I.e. if it's Tuesday, "next Thursday" isn't the Thursday two days from now but the Thursday 9 days from now.

  • I can't express the amount of visceral discomfort this brought me.

  • I've also started using it recently and I'm not sure if the way I'm doing it is particularly "right".

    I don't have a lot of knowledge of practical coding practices because in school we literally had a new project every two weeks so I never learned things like you need unit tests or proper architectural design. It was mostly making sure whatever project there was that week ran and didn't crash.

    So now I'm working as a sysadmin doing the random junk a sysadmin gets pushed on them. What I've been doing is telling it my project plan, Claude will write up something that looks better, and I continue to have a back and forth about architecture and libraries, asking it if it thinks any particular idea is good or bad, until I get to a place I'm happy.

    Then because I want to learn rust and implement it myself, I'm having Claude basically guide me through creating it like a teacher would, with it taking on a very Socratic tone ("now that we've done this, what do you think is the next step?" "We have a list of CSVs so what do you need to do to read their values?"). And I've been moving forward but by bit like this.

    I don't know if it's a particularly good way, honestly, I'd love feedback from anyone who's done something similar or whatever!

  • The liberux nexx, recently announced they're still trying to get the phone out and it has a headphone jack!

  • Deleted

    Permanently Deleted

    Jump
  • I use AI as a rubber duck, to compliment the rubber ducks on my desk when they don't give enough feedback. So it's use is mostly conceptual, I find that models that provide "thinking" output perhaps more useful than whatever its actual answer is because it asks questions about edge cases I might not have considered.

    As for code generation, I hate it. It outputs garbage, forgets things, hallucinates, and whatever thing it writes I'll have to rewrite anyway to actually make it compile.

    As I'm fairly isolated at work I think it makes a good pair programmer partner, so to speak. Offering suggestions that I can take into consideration and research heavily if I think it's a good one.

  • Yes, but that it can be temperamental and finicky. If you have a rooted phone currently you need to trick a different service called play protect into thinking that your device is kosher, so to speak; different updates from Google can and have broken the processes that have worked in the past.

    Needless to say a solution needs to be robust, the possibility to not access your gov id because a private company changed a process and decides you don't get to use the same loophole you've used till now isn't great from a technical or security standpoint. I would imagine it's even more frustrating for non-US citizens as their government is relying on a foreign company with a notably bad track record of keeping services available.

    It's not that such a technology is hard to make, it's more about adoption. Even better than a particular product we could gather around would be a set of standards that the community could build various products around (so long as they meet those standards). That however feels unlikely from the current US administration and based on the EU's recent GitHub proclamation on their age verification act.

  • I don't know if they'd even be up for it but at this point I think the best option would be Framework getting into it as theyre already trusted by the community.

    But even if we get the hardware down there's another issue - we need an open source, government approved, bank approved Wallet app. There's only Google or Apple wallet to store important documents on Mobile at the moment. Frustratingly, some governments are using only those two as a source for national verification which is obviously a problem.

  • Code in Rust and you can get double colons for your library path imports!

  • Really? I assumed postgres was the default for basically all open source projects

  • And yet, despite that was still responsible for less deaths than the CEO