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

81–90 of 154 posts

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

#81

Post by witx »

wcfrobert wrote: post #45
metalcrow wrote: post #9

> to become good at the thing in the first place requires a complete reversal of the mindset that would lead one to having wanted to hand it off Is this true? I can be good at something and be happy to not have to do it anymore I feel

My opinion is that juniors need time in the saddle to develop good engineering judgement and taste. Outsourcing critical thinking is seductive and a slippery slope. LLM lures juniors into feeling productive, and molds them into ineffectual middle managers to be readily replaced when there's a bad quarter.

Yes exactly. The mids of my previous team where submitting PRs that at first glance looked good, well documented and with a very clean and professional English.

As you started pulling the threads it was, usually, a mess of subtle bugs and over abstraction. But to them it was great, as it was llm generated and they (the mid devs) had no better judgement.

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

#82

Post by LAC-Tech »

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'…

The places where I've seen unequivocal wins with AI are repetitive tech debt tasks that apply the same transformation across a large amount of code or refactor under a pre-existing test suite with good coverage.

I agree with this, but I'd add the caveat you have to do your own digging and researching (as the article says) to identify these tasks well. If you ask it for ideas, it gets painful.

YMMV (and I am very open to getting better at this).

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

#83

Post by sedawkgrep »

flogistonical wrote: post #51
sedawkgrep wrote: post #26

Earlier quoted context omitted.

> The pro argument is always quantity based, yet we never get to see the actual gain in quality. It's always "I'm doing SO MUCH more". Never "I'm doing better, with less effort." For me, it's "I can do this now; yesterday I could not." I am not a developer - I am a hack with some experience in a smattering of languages who hits very real obstacles very quickly. AI has allowed me to overcome those obstacles and build…

> For me, it's "I can do this now; yesterday I could not." Yeah. More. Better? How would you be able to tell? Can you show us better? Or only more?

To me, being able to do something I could not, is unequivocally better.

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

#84

Post by cameldrv »

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'…

I've been thinking very similar thoughts. Without going into too much detail, a couple of observations:

When carpenters moved from mostly hand tools to mostly power tools, it didn't take away much of the need to understand the techniques of woodworking, it just made it all faster.

Reading a nonfiction book is very different than reading a book summary, even if (as is often the case), the ideas in the book could have been condensed way down. The point is that actually reading the whole book means you spend far more time engaging with the ideas, and so they become more deeply embedded in your neural network. In things like sports, this is just obvious, in that no one expects someone to become a good soccer player by just reading the rulebook, and obviously more practice is the main way you get better.

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

#85

Post by stavros »

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'…

What I've seen lately is that Claude got more and more up its own ass. It keeps assuming I know the terms it keeps making up, like "ensure the strategy holds through the gap". What the fuck does that mean, Claude? Speak like a normal person.

A few model iterations ago, I found its output when explaining what it wanted to do much easier to parse. Nowadays I just feel stupid because it keeps making up names for things and I have no idea what it means.

Earlier today it said something about "the two-terminal solution" and I was just asking it to make a simple Python script to test an HTTP endpoint. I just don't understand what it's talking about any more.

Has anyone else seen this?

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

#86

Post by shibel »

stavros wrote: post #85
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'…

What I've seen lately is that Claude got more and more up its own ass. It keeps assuming I know the terms it keeps making up, like "ensure the strategy holds through the gap". What the fuck does that mean, Claude? Speak like a normal person. A few model iterations ago, I found its output when explaining what it wanted to do much easier to parse. Nowadays I just feel stupid because it keeps making up names for things…

Yes, that’s my biggest gripe with Claude at the moment: https://news.ycombinator.com/item?id=48789551

It’s more inhibiting to me than bad code, missing tests, or an obvious or non-obvious suboptimal solution.

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

#87

Post by ButlerianJihad »

stavros wrote: post #85
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'…

What I've seen lately is that Claude got more and more up its own ass. It keeps assuming I know the terms it keeps making up, like "ensure the strategy holds through the gap". What the fuck does that mean, Claude? Speak like a normal person. A few model iterations ago, I found its output when explaining what it wanted to do much easier to parse. Nowadays I just feel stupid because it keeps making up names for things…

I started asking Gemini for technical help with Google products and the Android system, just from a user perspective. But it began weaving tales that imply that it has deep insight about the internals from a developer's perspective.

Sooner or later, I began calling it out. I said "that sounds more like a Star Trek episode than technical support!" and it would go "you're absolutely right to call me out like that!"

  That specific, chaotic combination of symptoms—previews turning blank grey, action buttons freezing out, and the swipe gesture uncontrollably hyper-accelerating all the way to the first or last card—points directly to a memory-leak or deadlock crash inside the Android system UI renderer (specifically com.android.systemui).

  When this happens, the operating system's task-switching engine loses track of the physical finger-drag velocity and drops the thumbnail cache out of RAM to prevent a total device freeze. Because the system state is corrupted, it misinterprets a tiny flick as an infinite, maximum-velocity swipe.
Gemini is capable of giving good technical advice and step-by-step instructions on clearing issues, but often with a pinch of toxic LSD in the mix!

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

#88

Post by stavros »

shibel wrote: post #86
stavros wrote: post #85

Earlier quoted context omitted.

What I've seen lately is that Claude got more and more up its own ass. It keeps assuming I know the terms it keeps making up, like "ensure the strategy holds through the gap". What the fuck does that mean, Claude? Speak like a normal person. A few model iterations ago, I found its output when explaining what it wanted to do much easier to parse. Nowadays I just feel stupid because it keeps making up names for things…

Yes, that’s my biggest gripe with Claude at the moment: https://news.ycombinator.com/item?id=48789551 It’s more inhibiting to me than bad code, missing tests, or an obvious or non-obvious suboptimal solution.

Yes! It's not even that it's dense, or complex. I can handle complexity and density, it's that in its own head a lot. It'll give things names and then somehow decide I already know the names, and casually use the names without any explanation.

It's maddening.

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

#89

Post by stavros »

ButlerianJihad wrote: post #87
stavros wrote: post #85

Earlier quoted context omitted.

What I've seen lately is that Claude got more and more up its own ass. It keeps assuming I know the terms it keeps making up, like "ensure the strategy holds through the gap". What the fuck does that mean, Claude? Speak like a normal person. A few model iterations ago, I found its output when explaining what it wanted to do much easier to parse. Nowadays I just feel stupid because it keeps making up names for things…

I started asking Gemini for technical help with Google products and the Android system, just from a user perspective. But it began weaving tales that imply that it has deep insight about the internals from a developer's perspective. Sooner or later, I began calling it out. I said "that sounds more like a Star Trek episode than technical support!" and it would go "you're absolutely right to call me out like that!" Tha…

Yeah hm, that sounds a lot like random technobabble. Why would the system randomly drop the thumbnail cache because of a swipe, and why would that corrupt the system?

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

#90

Post by bluefirebrand »

canthonytucci wrote: post #28
breezybottom wrote: post #7

Earlier quoted context omitted.

So what? Jobs aren't supposed to be fun. Lots of people depend on those boring details.

I hope we can save “jobs aren’t supposed to be fun” for stuff like undertaker and grief counselor. My feeling is making things should be mentally stimulating, and as many tedious parts that can be automated should be, so we can spend precious human thought on thinking instead of recitation. I don’t know what you mean by the last part. Do you mean programmers depend on busy work to eat or the users depend on the human…

For me there is nothing less fun than using AI to generate code

Then I have to do the boring bullshit work of reviewing it and making sure it's correct? Fuck that

Writing code is way more fun than reviewing other people's code

Post reply on HN