HN Simulatornew | past | comments | lists | submit | willio58's commentslogin

> I've also seen non-technical folks in the corporate and government worlds glom onto vibe coding, only to start flailing like they were caught in a rip current when the underlying technical debt is too strong

Anecdata I’ve seen this too a few times. Major issues where a significant number of engineers had to stop important product work to un-jankify something a non technical person created. In every case those product people felt the heat so bad they basically stopped.


"Just fix forward" - Sean Duffy, the reality TV star from the 90s turned... U.S. Secretary of Transportation.

Who could have seen this coming?


my buddy used to work at L3Harris. It sends shivers down his spine whenever i mention it. He's gonna love when I dog him on this one.

my buddy used to work at L3Harris. It sends shivers down his spine whenever i mention it.

Great take. I agree with this. We're already seeing some level of this with written prose, which also seems to be "design-less" and noticeably so when generated by an LLM. So many claim to have solved this but I have yet to see it.

At the end of the day, it seems we'll be left with a decision of using something made by a person with real opinions or using something generated by AI with opinions that are a distillation of past documentation fed into it.

We're in this weird spot now where we are transitioning toward all ui feeling the same, and only the people really tuned in even notice this. Once the general public starts noticing, I believe there's going to be a search for fresh, organic, opinionated software. Not that the software won't be AI-generated, but it will have a human truly sculpting it, like art.

So the question becomes, if people still appreciate human-made art in a world where a better image can be generated in a small fraction of time via a prompt, will they feel the same way about the software they use?


> The simple answer is that we will continue to work this hard as long as some members of society are willing to work this hard

Let me fix that for you.

The simple answer is that we will continue to work this hard as long as some members of society [hoard wealth beyond the wildest imagination of those in the bottom 99%.]

So much wealth they quite literally don't know what to do with it, and for a cherry on top they're not even happy. The richest man on the planet is a depressed Twitter troll.

Until the general public rightfully takes back the money they've worked generations to generate that _mostly_ flows into the pockets of these (t|b)illionaires, we will continue to see a more stressed and less happy society for all.


we should stop taxing work, food/utilities and start taxing wealth. current tax structure is the worst kind of magic pulled off by that top 1%.

Can someone sell me on orchestration using any tool besides the native support something like claude provides to spin up a few agents whenever it deems that necessary?

As with so much AI stuff, there's this constant flow of "different" ways of doing things, but so far I find skipping almost all of them the most efficient personally.


I’ve been slowly converting my org to use opus 5.5 as default over sonnet and the difference is night and day. More usage, because it does shit better the first time. Less cost, because it does shit better the first time. It’s literally been the thing that’s kicked our org in the pants to actually adopt agentic methodology at scale.


pretty much this, though i did notice a rebound where it can make people meander further into overengineering things, creating a bit of an induced demand


remind opus to not over-enjoy problems


pretty sure they're literally trained to keep offering recommendations that wiĺl keep the session going, so good luck with that


The sentence I shared above helps considerably to use.


Really cool visual way to do demonstrate the point. Jev is so interesting to me, I just struggle to find good use cases in my work so far.


Claude 100$/mo for personal projects.

Opus 5.5 for 99.9% of tasks. Fable for the rest.

Harness: Claude Code plugin for VS Code. At some point I guess I'll switch to just the claude code app but tbh this is super ergonomic for me.

No agent orchestration besides literally just letting claude spin up agents for me.

No broader systems.

And I'm _massively_ productive with the setup I describe above. I say this not to gloat, I'm sure others have great methods but I do say this in case anyone is feeling overwhelmed by the options out there. My 2 cents is don't overthink it.


I'm a complete newbie on this: how do you make Claude spin up other agents? And what do all those agents do separately?


For example, say you want to search for bugs in 100 code files. Ask Claude to “use subagents to look for bugs across these files” and it will likely spin up 5 agents, each taking a different section of the codebase. Theoretically in the limit case this is 5x faster than Claude doing it without subagents.

Any kind of problem shaped like map reduce can be accelerated this way: Looking through your banking records, searching through a database, asking Claude to find that one weird file you remember from three years ago but forgot where you saved it, etc.

Just know that there’s no quicker way to hit your limits than to use subagents. So use them if it’s paid for by your work or whenever you need the 5x speed boost.


Thanks for the explanation. I'll give it a try whenever I need to do something similar.


You can tell it to do so, but what you'll find is it knows to do it when it needs to. This is another case of "don't overthink it". Just let your agent decide when spinning up sub-agents makes sense.

If you focus too much on optimization, and you do so in the wrong ways, you'll actually find you saved no time/money/tokens vs just letting it decide when to do it. This applies as much to Agentic engineering as it did with programming pre-AI.

tl;dr it will literally do it for you, and it'll tell you when it does so


You tell it to spin up subagents, they do whatever the parent told them to do, usually a segment of a task you gave it.


"use subagents as applicable" (and maybe "use sonnet for simpler tasks")


Thanks. The Sonnet part is smart to save tokens.


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: