hirvi74

I have thought about something kind of similar to your last paragraph.

Instead of having a web application with a typical frontend and backend, I have fantasized about thin UI/UX interfaces with an almost pure LLM backend. Just having one or more bots receive parsed http requests, CRUD-ing the data based on training and tool access, and responding back if necessary.

(I have a strong dislike for web development, so perhaps my fantasies are a form of escapism.)

I never knew there was a -R. =')

You clearly have never met me in person. I am like a walking, talking Jim Carrey character. I'm also well into adulthood. For some, the hyperactivity is what most people think, and it does not always die down in adulthood.

Do you mind sharing any code from what you have produced? People talk about LLM successes and failures, but what's there to really talk about when the code can speak for itself?

In case it is unclear, I am genuinely curious. I have great success with chatbots, but vibing coding has never gotten me further than a proof-of-concept.

I'm more worried about my fellow humans than some personified algorithm.

I was diagnosed as an adult a little over a decade ago. I am still waiting on that "relief" part to come. Most days, I wish I never went through the diagnostic process in the first place.

Acceptance of the fact that I will always have executive function difficulties and there is nothing that can really improve it. It's not the realization I wanted to have, but it is one I wish I learned earlier.

ADHD here, as well.

> it was just not effective in tackling what I really needed.

That's how I would summarize my experiences with psychotherapy too. I think the only thing I have truly learned from therapy is what I feared most. There ain't much in this universe that can truly help with ADHD. Medications and other interventions barely move the needle for me. Seriously, I am at the point in my life where I am basically done fighting the condition. It's a Sisyphean effort that's mostly fueled by arbitrary societal expectations and my own egotistical desires and insecurities.

Negative, Ghost Rider.

I had many classes in college that didn't administer homework or take-home assignments. All we had were just exams. Most of those professors operated on the logic that if you wanted to pass their class, then you would do the (suggested) work.

Also, I never had a computer science class where exams were administered on a computer. I only graduated like 10 years ago, too. I shit you not, even my x86 assembly class was all pen and paper too, and yes, we were graded for code accuracy.

> There is an argument that universities should not be vocational, and should teach people how to be better humans, not better employees. I agree completely with this, but that also means universities need to stop advertising how getting a degree leads to more lucrative employment. Which is it?

I read a reply to a similar question in a different HN thread a while back that stuck with me. It went something like, "The point of university is to get an education. The point of student loans is to get a job."

I find that Siri AI cannot really do anything that I need, which is my major problem. I was truly hoping for Shortcuts to be a bit more beefed up with the introduction of Siri AI. For example, I was hoping that Siri AI could fix some of my annoyances like dismissing all notification banners. Of course, Siri AI cannot see nor work with notifications, so that's a huge bummer.

For normies, it might be nice to be able to add n > 1 reminders or calendar events, fix some grammatical errors, or whatever, but that's not particularly useful for me. I was hoping for a bit more of an AI that is truly integrated with the OS. Meanwhile, I feel like it's the worst model Gemini has to offer.

Moving an application window to another space without a mouse would also be nice. I've only wanted it for, like, the past 10-15 years. Snow Leopard even had that ability. Why was it removed? That's beyond me.

I have had to work around it with the most hacky scripts possible, and it's been so annoying trying to maintain all those scripts over the years.

Potency is an interesting subject because in theory one should have consume less amounts over the same time period for the same effect. In other words, smoking one potent joint, while carrying its own risks, is probably healthier than smoking n > 1 joints to get a similar effect.

Cannabis, the literal plant, is strong than the 70s, but it's not like humans haven't been making concentrates (hash, resins, etc.) for 1000s of years.

All I read about if productivity, but where are all the products? I keep reading about a lot of work, and I still see little to show for it. Why is the vast majority of software still utter shit (and getting worse)?

I think our entire field would benefit from us taking the time to think a bit more. I have no opposition to LLM usage either.

LLMs have made me enjoy programming even more than I already did. No, I don't use them to program for me, but I love having an on-demand entity to ask any question I desire.

I've been finally working on a plethora of ideas that I have put on the back burner. I think my favorite aspect of using LLMs has been the reduction in friction. Mind you, I predominately use the chatbots, I still love how I can go from 0 to 60 in mere hours with languages and stacks I am complete unfamiliar with. In the past month. Chatbots are great for one demand documentation.

Lately, I have had LLMs create little "drills" for me. I have them suggest poorly written, flawed, or buggy code (like a function at most), and then the goal is for me to try to figure out how to write it better and compare my answer with the LLM's instant feedback. These are dumb, little, fun games I play to pass time, but I feel like it's better than doom-scrolling.

As for letting LLMs do the work, I've tried vibe-coding, and I utterly hate it. If you love vibe-coding, then I won't try to take it away from you. I just never like the results I receive. I read every single line produced, and I am never satisfied with the code. It's always an utter mess or full of shortcuts. An LLM could replace me tomorrow, no question. I have to give the bots credit. I am not a particularly impressive programmer in any regard. I am probably slightly below-average to average after a decade of experience.

Still, I am insecure and controlled by my ego -- if an LLM produced it, you did not make it. Maybe I am vain, but I want all the credit. If I produce something, I want to tell people that I made it.

Isn’t that to be expected when comparing one 20x plan to another 5x plan?

I am curious how the 5x plans differ between both providers.

Sorry if I am misunderstanding you, but I am pretty sure the $100 plan doesn’t have a 5hr usage limit. So, if that was what was preventing you from going non-stop, it might be worth it.

I am considering the plan myself. I just don’t know if I want to fork out $100 per month for something I will make $0 off of.

I wanted to like Siri AI, but it does not really do anything that I need at the moment.

I was hoping Siri AI could help more in the GUI automation world, but it seems that is not the case.

For example, I was hoping Siri AI could create a Shortcut that would clear/dismiss all notification banners. Nope, it can’t even access nor see notifications.

I have my own scripts and whatnot to handle these desires, but I am just tired of having to rework a lot of them for each OS release.

I'm a born and raised the Southerner, so I don't really understand all this "Effective Altruism" and "Rationalist Movement" group stuff.

Seriously, I am not trying to be obnoxious or make some poor attempt at a joke. I used HN for years before I learned YCombinator was like Shark Tank for startups or something.

So, to my knowledgable folks in this thread, are these groups truly some efficacious, philanthropists, or are these movements just another one of those onanistic Bay Area beliefs I see people complain about a lot on the Internet? (No hate here, I've never even been to the Bay, nor have I met any tech folks from there either).

I tried to read the article, but with all the proper nouns and acronyms, I might as well have been reading a foreign language.

I'm, like, 99% sure I am dyslexic. So, I might be the worst example of spoken and written language usage possible.

Is the saying commonly the other way around? I swap word orders, structures, etc. all the time (amongst many other mistakes), so I didn't even notice I wrote it like that until you mentioned it lol.

"Hey Claude, where should I bomb Iran? Make no mistakes."

Well, if the map image I saw initially after the bombing was correct, then the facility did not used to be a school. The building had different, military purposes as it was attached to a military base, and later was converted into a school. My understanding is that the AI that was used to facilitate this attack was trained on maps where the building was still used for military purposes some years back.

It absolutely does not excuse anything, but I suppose that might explain the denial at first. I cannot explain any further denial though.

The new Siri AI is so incredibly disappointing. I only wanted one thing, and one thing only -- enhanced automation. I don't give a fuck if Siri AI can edit little pictures or some bullshit. I wanted something that could actually replace AppleScript/Automator to a useful degree. Something that actually could interact with the system. Of course, that is asking for too much.

Still no way to move an application window from one space to another without a mouse. If you have a disability, then I guess you cannot really use spaces, which is poor design. But it's not like Apple cares. Snow Leopard had this ability back in 2010. Why it was removed is beyond me.

I am die hard Apple fanboy, but I feel ashamed for having hope in '27.

My understanding is that having certain genes makes conditions like Autism more probabilistic than deterministic.

> To what extent are people still coding by hand these days?

That's basically I all do. I might ask a few questions to LLMs here and there like Google/StackOverflow in the days of yore.

Still, every line in all my codebases are still hand-typed. I get everything I need out of the chatbots, and I cannot use any kind of agentic coding tools at work, oddly enough. Trust me, I'd love to have access to something like Codex at work. That way I could save my mental bandwidth for personal projects that I find interesting and enjoying.

If AI ever truly becomes some super-intelligence far beyond people's comprehension, then how could we even predict how things turn out? If things go poorly in the future, then I can absolutely see it being something unpredictable.

There is a lot of hubris in predictions about LLMs. If an AI were so intelligent, then it would probably be intelligent enough to want nothing to do with us.

Still, I worry more about other humans than I do LLMs. Our fellow mankind will probably wipe us out before LLMs do. That, or the Earth will punish mankind for our cruelty, vanity, and disrespect.

Maybe true, maybe false. However, I sense Mircosoft is also jealous that their AI products are worse than useless. They'd be singing a different tune if they were in Anthropic's position.

That's pretty much most T1 support already. I feel like all I do is talk to bots.

I resonate with this sentiment. I want AI to be used at my job for 100% of the code so that I may go home and use my mental bandwidth to work on projects I actually find interesting.