Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

It's not empowering to hand off the details

davidnicholaswilliams.com

Post reply on HN
Print view View original

121–130 of 154 posts

Re: It's not empowering to hand off the details

#121

Post by mrbnprck »

anditherobot wrote: post #60

AI can generate what a company makes. Can it generate what a company is? Producing artifacts: media, code, documents, the visible output has clearly gotten easier. But the other things, like knowing what's worth building in the first place and making the right judgment call, still seem to be left to the humans.

There already are use-cases for automatic software deployment where monitoring is ingested back to the AI, which then judges to rollback/fix a feature if certain metrics spike/user complaints arive.

If you had the data basis (user reports, trends, ...) you could let the AI decide upon that what to build.

Re: It's not empowering to hand off the details

#122

Post by theshrike79 »

radicality wrote: post #66
RGS1811 wrote: post #19

I've been vibecoding a ton for the past 9 months, built a bunch of cool little apps for myself with AI, ran experiments, built an entire SDLC on skills, did the agent orchestration harness thing, etc. In the past few weeks I've hit a wall where I'm just tired of it. Each model becomes more independent but also harder to direct in detail. They produce massive, tedious, sloppy text outputs with very little input. They'…

Similarly for me. I have a recent example too. I run a bunch of eps32 devices at home, using esphome. Pre-AI I wrote all the yaml myself and understood what’s happening and didn’t have any very bespoke hacks. Recently I asked an agent for a feature where the screen will get dimmer after some time, and eventually after a day the screen will turn off and then turn back on if I tap, which should be pretty easy in esphom…

For some reason some harness/agent combos are deathly allergic to adding more dependencies unless you explicitly allow it.

Then you'll get shit like custom JSON parsers or config parsers made from scratch instead of importing an industry standard library.

Re: It's not empowering to hand off the details

#123

Post by KronisLV »

johnfn wrote: post #102

But surely at some point you need to stop, right? Most web developers are perfectly capable without understanding the intricacies of the file system or OS, even though the browser sits on top them. Most engineers don’t know assembly, or transistors or electrical engineering. Steve Jobs didn’t know every line of Objective-C that went into OSX. I don’t think Michelangelo collected all his paint materials by hand when p…

> Most web developers are perfectly capable without understanding the intricacies of the file system or OS, even though the browser sits on top them.

This will mess you up if you ever need to store a significant amount of files on the file system directly, or even deal with resource usage for batch processes, or have to dig into non-trivial transaction handling when dealing with DBs without having learnt enough about them, or even the whole domain of SQL and query optimization that ORMs will not protect you from and so many other things.

I don't think you need to know everything, but you definitely need to learn.

> But surely at some point you need to stop, right?

I guess, but typically due to your own lack of curiosity or mental exhaustion, or even limited time to spend on something, rather than the new knowledge and skills not being good to have. At least knowing when AI is heading in the wrong direction for any given domain will save your bacon.

Re: It's not empowering to hand off the details

#124

Post by theshrike79 »

hahahaa wrote: post #14

You develop a taste as to what details you can skim and what you need to dive on. We are all trained on this due to doing 10000 wax on wax off movements, called a "PR Review". I used to scrutinize. Now I think "yep that bit looks good and tests will catch errors plus I can manually test. This bit over here looks scary will spend time more deeply understanding". With AI you don't need to understand every line in depth…

"Code Smell" is the term I use here.

With enough experience you can just glance at a diff and see if it "smells". If it does, you drill down and see if you were right. If not, you trust the process and approve.

(And I'm talking about basic run of the mill code here, if you're doing something that kills people, don't go by feels)

Re: It's not empowering to hand off the details

#125

Post by theshrike79 »

skydhash wrote: post #115
iepathos wrote: post #98

Earlier quoted context omitted.

If I commission a part specified as 10.00 ± 0.01 mm, I can verify it with a calibrated micrometer without understanding the CNC machine, its software, or how to manufacture the part. Likewise, a function with a finite input space can be exhaustively tested against its specification without understanding its implementation. In these cases, I need to understand the requirement and the test, not the production details,…

> If I commission a part specified as 10.00 ± 0.01 mm, I can verify it with a calibrated micrometer But there is someone that needs to design that part, specify the material needed and a few other things. The actual verification is fast because someone has compiled the list of checks. And compiling that list of checks is hard work. In other words, where '10.00 ± 0.01 mm' comes from is very important. That's why peopl…

No, the code isn't what defines it. It's the tests and specs around it.

Code should never be the only source of truth.

Another shitty analogy: baking.

Saying "code is the medium of the definition" is like saying "the cake is the medium of the recipe". So anyone wanting to make the cake or change how it's made should just dive into the cake and start analysing it.

That's why we have recipes, and even they can be modified as long as the exepectation is met: It has to be sweet, soft, covered in something white and must have strawberries inside.

Code should be the same, I should be able to toss the whole codebase in the trash and regenerate it from the tests and written specifications. If I can't there's something wrong with the process.

Re: It's not empowering to hand off the details

#126

Post by exe34 »

breezybottom wrote: post #59
exe34 wrote: post #27

Earlier quoted context omitted.

Some of us just wouldn't work if it wasn't fun. I'd let myself starve in the streets. (I have some experience with starvation from an eating disorder phase in my twenties, it's only unbearable if you have to work).

Easy to say when you're not at risk of starving.

I like how you ignored the second part of my post. I specifically included it because I knew someone would respond like this to the first part. I think it's actually feasible when you have no other options - it's my retirement plan anyway.

Re: It's not empowering to hand off the details

#127

Post by theshrike79 »

slopinthebag wrote: post #6
cheevly wrote: post #3

Every word of this seems objectively false. AI is more than capable of handling the details. I have generated countless tools for myself without needing to know or care about the details.

It’s always tools tho, and AI tools especially. Why not anything else?

Because creating bespoke deterministic tools with AI is an excellent use-case for it.

Even if the AI goes away or is enshittified, the tool still remains. And you get to do less of the boring shit because the tool does it for you.

Or you replace some montly cost application you use maybe 10% of with a custom thing and save money each mont.

Re: It's not empowering to hand off the details

#128

Post by blks »

Sharlin wrote: post #76
existencebox wrote: post #50

Earlier quoted context omitted.

I expect there's a probabilistic factor to it, among other things. I use the almost the same addendum as you ("do not make, commit, or push any changes without my approval") and it broadly seems to work in my day-to-day dev. However, I also set up some agents that trigger on incoming requests from my dev teams to automate things that used to be rote/manual tasks. _That_ is where I see the issues, I suspect simply bec…

I haven’t used these tools that permit LLMs to make changes on their own, but I can’t help being baffled if there’s no big red switch that changes the system prompt and disables any and all write access to the outside world.

I think the best way is to run agents under Unix user that has very limited rights (eg only read only) for project folder and the rest of the system. It’s kind terrifying how people run agents on their computers without any hard limitations, just hoping they will follow instructions and not do anything malicious. This is basically a trojan waiting to happen, either trying to solve something by all means possible, or getting prompt injection

Re: It's not empowering to hand off the details

#129

Post by theshrike79 »

tpmoney wrote: post #91
jclardy wrote: post #46

This is what a lot of people miss. People think, "Oh we won't need software soon, AI can just build interfaces when we need them" but in reality, the software was built to solve a problem, usually by people invested in solving that problem. Saying "Build me a todo app" will give you the sum of averages, a completely average todo app that works fine, but it isn't great in any measure. The details are what separates th…

I agree with your first part, that software is built to solve a problem. But I think you sort of sidestep what makes AI exciting to non-software people with your second part. The people who are excited about this aren't excited because they can ask for a todo app but because they can solve the problem the todo app was supposed to be soling for them without needing to find and learn a todo app. AI is the new "excel sp…

> AI is the new "excel spreadsheet with ridiculous formulas on top of VB script on top of pivot tables" for the non-programmers.

This is exactly it. Moving all those abominations to bespoke applications at least lets us (Actual programmers) provide them with the tools to make their solutions a bit less bad. Linters, unit tests, code formatters etc. will make even the crappiest "this would've been a complex excel spreadsheet in the past" solution at least manageable.

And if a company doesn't have a workflow for supporting these, they'll either have a whole ass problem with people doing it without telling anyone or should get on it immediately.

Re: It's not empowering to hand off the details

#130

Post by samrus »

hollowturtle wrote: post #63
raincole wrote: post #31

Earlier quoted context omitted.

> as an assistant that helps me make decisions, and ensures that I'm in the driver's seat This... quite describes what the current AI feels like to me. So I really don't see a problem. If AI does too much for you, you should, uh, just prompt it to do less. Everyone talks about how their AI escapes sandbox and virtualization or delete their entire repos or something. Perhaps they're using a skynet I'm not aware of. Fr…

> From my experience when I added "discuss; don't edit any file yet" at the end of the prompt I've never seen the LLM go against my will and edit the files anyway. depends how long conversation gets and he will still ignore your instructions randomically. I think shorter sessions are better, I do have a similar prompt saved on the memory of the agent and way more times that I can tolerate, he candidally ignores it

Shorter sessions are most definitely the only way to go. I ensure thay by having a clean context handoff process and then using one session for one task and having it dump context when its done or gets too big (~400k tokens)
Post reply on HN