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

The creator of Claude Code's Claude setup

twitter.com

Post reply on HN
Print view View original

301–310 of 423 posts

Re: The creator of Claude Code's Claude setup

#301

Post by CuriouslyC »

tmerr wrote: post #65

This is interesting to hear, but I don't understand how this workflow actually works. I don't need 10 parallel agents making 50-100 PRs a week, I need 1 agent that successfully solves the most important problem. I don't understand how you can generate requirements quicky enough to have 10 parallel agents chewing away at meaningful work. I don't understand how you can have any meaningful supervising role over 10 thing…

The problem isn't generating requirements, it's validating work. Spec driven development and voice chat with ticket/chat context is pretty fast, but the validation loop is still mostly manual. When I'm building, I can orchestrate multiple swarm no problem, however any time I have to drop in to validate stuff, my throughput drops and I can only drive 1-2 agents at a time.

Re: The creator of Claude Code's Claude setup

#302

Post by vidarh »

CharlieDigital wrote: post #280
margorczynski wrote: post #266

Earlier quoted context omitted.

I'm not. That edge eventually converges to 0 when you have 10+ competitors that offer the same for 10x less money. If you don't have some kind of cult following like Apple eventually you'll get margin-squeezed till death and all that marketing, sales, etc. will get cut down to stay afloat. Of course all of the above is just my theory how this will play out in the long run, I'm no oracle by any means.

> that offer the same for 10x less money. Not likely because there is still a lower bound. These 1 person startups are winning partially because they are already 10x cheaper than the incumbents. But beyond that, it's not likely that there are 10x the number of people who know the domain and have the right mindset plus appetite for risk.

I'm not entirely disagreeing. There are limits there that means we can't assume the margins will go to their theoretical minimum. But you're also in part assuming the models don't increasingly know the domain or know how to research the domain and compile the information for you.

They'll be squeezing margins out of a lot more than just the tech.

Re: The creator of Claude Code's Claude setup

#303

Post by lunar_mycroft »

CharlieDigital wrote: post #241
crystal_revenge wrote: post #169

Earlier quoted context omitted.

My initial response to reading this post was "wow, I think I'd rather just write the code". I also remain a bit skeptical because, if all of this really worked (and I mean over a long time and scaling to meet a range of business requirements), even if it's not how I personally want to write code, shouldn't we be seeing a ton of 1 person startups? I see Bay area startups pushing 996 and requiring living in the Bay are…

> shouldn't we be seeing a ton of 1 person startups? Here's the dirty secret: 1 person AI coding enabled startups don't want their customers to know that they are 1 engineer AI coding startups so they do not expose it or share that info. There is still a lot of negative sentiment associated with this. I know 3 such founders; none would advertise to their customers the extent of their AI usage. There is also a conside…

As of the middle of the year, there was no increase in publicly available indicators of new startups at all [0]. No change in the trend in steam releases, domain name registrations, app store releases, etc. People might be able to keep the fact that they're a one person team that built the app with AI secret, but they wouldn't be able to keep the fact that they made an app secret. Unless someone has evidence that's changed dramatically in the last six months, I have to conclude that the reason we aren't seeing a wave of AI enabled SaaS startups isn't that they're keeping the fact that they're solo operations with AI a secret, but rather that no such wave actually exists.

[0] https://mikelovesrobots.substack.com/p/wheres-the-shovelware...

Re: The creator of Claude Code's Claude setup

#304

Post by CuriouslyC »

margorczynski wrote: post #252
CharlieDigital wrote: post #241

Earlier quoted context omitted.

> shouldn't we be seeing a ton of 1 person startups? Here's the dirty secret: 1 person AI coding enabled startups don't want their customers to know that they are 1 engineer AI coding startups so they do not expose it or share that info. There is still a lot of negative sentiment associated with this. I know 3 such founders; none would advertise to their customers the extent of their AI usage. There is also a conside…

But eventually people will catch up you can basically create a working product alone with the help of AI. My prediction is that this will lead to a margin free-fall for many software products where the main moat is the software itself. And a lot of SaaS companies will also become redundant when the AI can code up a tailored solution in an hour for free.

This is mostly correct IMO.

SaaS is extremely vulnerable, companies will be able to modify open source tools to do exactly what they need, and agents will make managing those services easier. This will lead to downward pressure on SaaS prices, and cause them to become more like cloud data management platforms that they let customers build on top of rather than one-size-fits-all apps.

Re: The creator of Claude Code's Claude setup

#305

Post by neomantra »

stingraycharles wrote: post #128
tmerr wrote: post #65

This is interesting to hear, but I don't understand how this workflow actually works. I don't need 10 parallel agents making 50-100 PRs a week, I need 1 agent that successfully solves the most important problem. I don't understand how you can generate requirements quicky enough to have 10 parallel agents chewing away at meaningful work. I don't understand how you can have any meaningful supervising role over 10 thing…

I hope self-promotion isn't frowned upon, but I've been spending the past months figuring out a workflow [1] that helps tackle the "more complicated problems" and ensure long-term maintainability of projects when done purely through Claude Code. Effectively, I try to: - Do not allow the LLM to make any implicit decisions, but instead confirm with the user. - Ensure code is written in such a way that it's easy to unde…

Thanks for sharing and taking the time to document your repo. I’m also sometimes unsure of “self-promotion” — especially when you don’t have anything to sell, including yourself.

I sometimes don’t share links, due to this and then sometimes overshare or miss the mark on relevance.

But sometimes when I do share people are excited about it, so I’ve leaned more to sharing. Worst is you get some downvotes or negative comments, so why not if there is some lurker who might get benefit.

When you don’t blog or influence, how else but in related HN comment threads are like-minded people gonna know about some random GitHub repo?

My second level hope is that it gets picked up by AI crawlers and get aligned somewhere in the latent space to help prompters find it.

ETA: “The [Prompt Engineer] skill was optimized using itself.” That is a whole other self-promotional writeup possibility right there.

Re: The creator of Claude Code's Claude setup

#306

Post by djeastm »

TheRoque wrote: post #130
bizzleDawg wrote: post #93

I spent a whole day running 3x local CC sessions and about 7 Claude code web sessions over the day. This was the most heavy usage day ever for me, about 30 pull requests created and merged over 3 projects. I got a lot done, but my brain was fried after that. Like wired but totally exhausted. Has anyone else experienced this and did you find strategies to help (or find that it gets easier)?

Did you manage to make proper reviews of all the 30 PR ?

I think we all know the answer to that.

Re: The creator of Claude Code's Claude setup

#307

Post by CuriouslyC »

ecb_penguin wrote: post #297
democracy wrote: post #208

Earlier quoted context omitted.

So true, as a mere software developer on a payroll: I might spend 10 minutes doing a task with AI rather than an hour (w/o AI), but trust me - I am going to keep 50 minutes to myself, not deliver 5 more tasks )))) And when I work on my hobby project - having one AI agent crawling around my codebase is like watching a baby in a glassware shop. 10 babies? no thanks!

[flagged]

A lot of orgs are bad about giving credit to employees for productivity, what's the point of working 4x harder if it'll just result in a few % point difference in yearly raise, and you're still going to have to job hop to get a respectable pay bump? Might as well work less and spend time polishing your resume/side projects to make yourself as employable as possible. This is 100% the fault of poor incentives on the part of employers.

Re: The creator of Claude Code's Claude setup

#309

Post by gedy »

tmerr wrote: post #65

This is interesting to hear, but I don't understand how this workflow actually works. I don't need 10 parallel agents making 50-100 PRs a week, I need 1 agent that successfully solves the most important problem. I don't understand how you can generate requirements quicky enough to have 10 parallel agents chewing away at meaningful work. I don't understand how you can have any meaningful supervising role over 10 thing…

> This is interesting to hear, but I don't understand how this workflow actually works

The cynic in me is it's a marketing pitch to sell "see this is way cheaper than 10 devs!". The "agent" thing leans heavily into bean counter CTO/CIO marketing.

Re: The creator of Claude Code's Claude setup

#310

Post by CharlieDigital »

lunar_mycroft wrote: post #303
CharlieDigital wrote: post #241

Earlier quoted context omitted.

> shouldn't we be seeing a ton of 1 person startups? Here's the dirty secret: 1 person AI coding enabled startups don't want their customers to know that they are 1 engineer AI coding startups so they do not expose it or share that info. There is still a lot of negative sentiment associated with this. I know 3 such founders; none would advertise to their customers the extent of their AI usage. There is also a conside…

As of the middle of the year, there was no increase in publicly available indicators of new startups at all [0]. No change in the trend in steam releases, domain name registrations, app store releases, etc. People might be able to keep the fact that they're a one person team that built the app with AI secret, but they wouldn't be able to keep the fact that they made an app secret. Unless someone has evidence that's c…

Can't speak for anyone else, but I personally know 3.

2 of the 3 existed as entities for more than a year already, but pivoted at least once (both were VC-funded but now doing something very different than what they started with when I first met founders) and ultimately let go of their offshore and contract engineers once AI became good enough some time early last year. Founders basically realized that the quality of code was as good or better than what they were getting from their engineers while reducing the turnaround time; now they can go from talking to customers to having a working prototype in the same day instead of waiting 24h+ for an offshore team. The other one started in November of 2024 and found traction around March.

So two companies went from multi-person teams to 1 person teams and 1 team was a 1 person eng team from the get-go (with a business-oriented partner).

I'd also point out that 2025 was a particularly volatile year because of shifts in the political and economic environment (including very high interest rates) so I wouldn't take your stat at face value without considering external factors that might affect the total number of net new business registrations.

It still remains true that building a product is not the same thing as building a business. It may be that we'll see less SaaS startups as companies find that they can just in-house software instead of buying. Who knows? Startup I'm at canceled one of our subscriptions because we ended up building an in-house replacement because it is now cheap enough and easy enough that we could.

Post reply on HN