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/)M

MangoCats

@ MangoCats @feddit.it

Posts
0
Comments
1701
Joined
2 yr. ago

  • Side of slop? Bizarre AI food images jump from online to IRL menus

    Jump

  • That's not acceptable, that's not professional, somebody is going to eat that burrito - are you going to file their permission to use the image of their food? Too complicated.

  • Side of slop? Bizarre AI food images jump from online to IRL menus

    Jump

  • OpenClaud is clearly an amalgam of most AI agents out there, a very accurate one.

  • Side of slop? Bizarre AI food images jump from online to IRL menus

    Jump

  • Boss said add a picture, I said artist costs money, boss said "use AI" - just doin' my job.

  • Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice

    Jump

  • For professional work we hire experts (who use AI as their first pass, but then "clean it up" to their "high professional standards using native speakers") - and then we do another pass with "subject matter experts" who both speak the language and work directly in our field, becaue the "professional humans" typically don't have those niche experiences. We recently made this procedure 100% required after the "human professionals" effectively translated On to mean Off for one of our controls...

  • 111 mph: Brevard Deputy of the Year avoids arrest under Florida ‘Super Speeder’ law

    Jump

  • Not only the courts, I find many areas of life where "right and wrong" are best treated as a sort of ideal, aspirational thing, not something to invest a lot of energy in upholding - if you're interested in overall quality of life. Especially when dealing with our (disabled) children and the school system, but also medical malpractice and other situations, there are fights we could have taken to court, fought hard - at great personal expense not only of legal fees but also time and emotional energy - and won the court case, but lost overall in terms of achieving the things we really cared about - that time and money was put to much more productive and life enhancing uses than "making a stand and proving the injustice." You can argue that we "shirked our duty to society" by allowing the injustices to continue, I argue that society shirked its duty to itself by making tthe injusticies so individually costly to expose and correct.

  • 111 mph: Brevard Deputy of the Year avoids arrest under Florida ‘Super Speeder’ law

    Jump

  • I agree about seatbelts - though if I lived 3 or 4 near-death experiences where seat belts made my outcome worse instead of better, I'd probably say to hell with the odds...

    I know a lot of people who have spent time in the court system, other than ambulance chaser backed situations, I don't know many happy with the outcomes.

  • 111 mph: Brevard Deputy of the Year avoids arrest under Florida ‘Super Speeder’ law

    Jump

  • I agree to disagree - most times I have ended up in court I could have made choices to stay out, on balance I feel that even when I have won in court by preparing and going I still lost overall and so, most times those were bad decisions to go, fight and win.

  • Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice

    Jump

  • Also good at translating both spoken languages

    I know more than a few fluently multi-lingual people who would just roll their eyes...

  • Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice

    Jump

  • There definitely are tasks where using the "standard tools" goes far faster than asking the LLM to do it for you, such as: copying signatures from images onto a .pdf contract - they're pretty hopeless at editing out background noise, etc. but if you clean up the signature input images enough, they'll take it home and make the ink solid and the background transparent and overlay them in the .pdf faster than you can open the four files in Photoshop or whatever your tool of choice is.

    By the way, images of signatures on electronic documents have been an outrageous farce since 20 years now, LLMs just make it easier than ever to edit them into an existing .pdf

    Thing is, there's literally millions of common "computer tasks" and the LLMs themselves are just starting to "learn" which ones they're good at and which they are not. It would be cool if Opus would self-identify "hey, I'm really good at this..." and "I'm pretty challenged with that, you'd be better off downloading this FOSS tool and doing it yourself, here are helpful instructions..."

  • Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice

    Jump

  • Bitcoin had a slower rollout, it wormed its way into smaller niches. A lot of early bitcoin mining was done on "borrowed" or otherwise "unused" hardware that other people paid the electric bills for.

    I generally approve of much of what cryptocurrency could be used for, but I've been pissed off about the waste of proof-of-work cryptocurrency since before 2018, and nothing has improved since then.

  • 111 mph: Brevard Deputy of the Year avoids arrest under Florida ‘Super Speeder’ law

    Jump

  • Staying out of court is the real win.

  • Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice

    Jump

  • The real problem with "bad" AI code is that it compiles, without errors or warnings. It passes all the unit tests. It passes all the integration tests. At least it will if you tell it to keep iterating until it does. Some days that may be a spaghetti mess, some days that's all you need.

    If you develop a modular architecture with sufficiently fine grained modules, the spaghetti comes in managable portions.

  • Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice

    Jump

  • Nobody forced me to adopt AI, and up until about a year ago I mostly ignored it. It "wasn't ready for prime time" back then. Starting about a year ago, I saw the improvement curve and the potential and decided it was time for me to learn how to make the best of it. Starting about 8 months ago it really turned a corner in terms of productivity and usefulness, and that same increase in productivity is driving improvement in the AI tools themselves. I expect it to plateau, any day now, but so far it doesn't seem like it has started - each new "frontier model" seems noticeably more capable / useful than the one before. Sometimes that's more a matter of specialization than general overall capabilities, but that's O.K. too - we don't need one model to serve all purposes, that's the whole M.o.E. premise...

  • Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice

    Jump

  • all the programmers pushing AI on me like Crypto Bros while their programs work worse are smart, well intentioned people?

    Sorry, if you just think back to the 1990s, you're describing the Microsoft shitshow, pushing "updates" that make things worse not better, pushing standard products that aren't as good as the products that were avaialble years earlier. Lately I've been getting the same vibe out of Canonical / Ubuntu.

  • Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice

    Jump

  • An LLM cannot understand intention, it just makes statistical guesses that are often wrong.

    True, when you give a prompt like: "make me a contact management / constant contact app which I can deploy on AWS and scale to 100,000 users." you get, mostly garbage. If you specify how you want the UX to flow, what fields are most important, what fields should be included in deeper interfaces, what the scheduling looks like, how it gets tuned, what the reports look like, etc. etc. etc. - in other words: give it real requirements and specifications.

    Then, pay attention as it develops, you'll ususally find that the requirements you gave it aren't exactly what you really wanted, and when you see what it built that doesn't match with your visions, you can have it revise the requirements and specs.

  • Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice

    Jump

  • AI or far-east coders, we encourage them to keep their PRs as small as possible.

  • Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice

    Jump

  • Prompting for refactoring, requirements, specifications, unit tests, integration tests, distribution / install scripts, all of those "good ideas" are things you need to nudge even Claude to do. Once you get it in the habit of doing them it does them automatically more often but still requires the occasional nudge.

  • Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice

    Jump

  • I have done several smaller projects with it, and they have been stable / performant for months - better than similar stuff I coded years earlier and spent 5-10x the effort on.

  • Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice

    Jump

  • I find that depends a LOT on what you're asking the LLM to write, how well you're specifying it, etc. As for the code reviews, if it's code that matters: remember to open a new instance and ask the exact same question again on the code that has been reviewed and "fixed". Back a year ago, that could get you into a waffle-loop where the engine would change its mind back and forth about what's optimal and just oscillate between the two. These days they seem to record (and read) enough context to prevent that behavior, but I definitely get behavior of: "Are there any bugs?" "Yes, here are seven bugs." "Fix those bugs." "The bugs are fixed." (and they ususally really are...) "Are there any more bugs?" "No, we have fixed ALL the bugs." "Are you sure, look again." "Yes, I am sure we have found and fixed ALL the bugs." --- new context window --- "Are there any bugs?" "Yes, here are seven bugs." different bugs.

    I did that on a bigger project and literally repeated 20 times, finding 140 real bugs - granted, the later bugs were getting pretty trivial / far out edge cases, but they were still real, still fixed, still denied there were any more bugs until opening a fresh context and asking again. This was on Google's Gemini 3.7 Flash High... Claude Opus 4.8+ seems quite a bit better about being able to continue in a context without becoming blind to issues "it has already solved."