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

Building a Personal AI Factory

john-rush.com

Post reply on HN
Print view View original

41–50 of 167 posts

Re: Building a Personal AI Factory

#41

Post by zackify »

simonw wrote: post #28

My hunch is that this article is going to be almost completely impenetrable to people who haven't yet had the "aha" moment with Claude Code. That's the moment when you let "claude --dangerously-skip-permissions" go to work on a difficult problem and watch it crunch away by itself for a couple of minutes running a bewildering array of tools until the problem is fixed. I had it compile, run and debug a Mandelbrot fract…

If it helps anyone else. I downgraded from Claude max to pro for $20 and the usage limits are really good.

I think they’re trying to compete with Gemini cli and now I’m glad I’m paying less

Re: Building a Personal AI Factory

#42

Post by azan_ »

apwell23 wrote: post #37

ppl are getting slowly disillusioned with vibe coding. yes AI assisted workflow might be here to stay but it won't be the magical put programmers out of job thing. And this the best product market fit for LLMs. I imagine it will be even worse in other domains.

Are they though? I’m seeing more and more people that used gpt4 and got substandard results get blown away with Claude code and opus once they gave it a chance. Also remember that progress has not stopped (whether it has slowed down is also controversial), so I wouldn’t make strong assumptions that ai won’t replace many devs. I hope it won’t, I really like intellectual work associated with it.

Re: Building a Personal AI Factory

#43

Post by petesergeant »

> I keep several claude code windows open, each on its own git-worktree.

Can someone convince me they're doing their due-diligence on this code if they're using this approach? I am smart and I am experienced, and I have trouble keeping on top of the changes and subtle bugs being created by one Claude Code.

Re: Building a Personal AI Factory

#44

Post by petesergeant »

lucubratory wrote: post #35
gerdesj wrote: post #34

Earlier quoted context omitted.

Crack on - this is YC! Why are you not already a unicorn?

An LLM wrapper does not have serious revenue potential. Being able to do very impressive things with Claude Code has a pretty strict ceiling on valuation because at any point Anthropic could destroy your business by removing access, incorporating whatever you're doing into their core feature set, etc.

Having worked with some serious pieces of enterprise software, I don't think this is right. Anthropic is not going to perfect multi-vendor integrations, spin up a support team, and solution architect your problems for you. Enterprise software gets into the walls, and can be very hard to displace once deployed. If you build an LLM-wrapper resume parser, once you've got it into your client's workflows, they're going to find it hard to unembed it to replace it with raw Anthropic.

Re: Building a Personal AI Factory

#45

Post by petesergeant »

apwell23 wrote: post #37

ppl are getting slowly disillusioned with vibe coding. yes AI assisted workflow might be here to stay but it won't be the magical put programmers out of job thing. And this the best product market fit for LLMs. I imagine it will be even worse in other domains.

> ppl are getting slowly disillusioned with vibe coding.

This is the absolute polar opposite from my experience. I'm in a large non-tech community with a coders channel, and every day we get a few more Claude Code converts. I would say that vibe-coding is moving into the main-stream with experienced, professional developers who were deeply skeptical a few months ago. It's no longer fancy auto-complete: I have myself seen the magic of wishing a (low importance) front-end app into existence from scratch in an hour or so that would have taken me an order of magnitude more time beforehand.

Re: Building a Personal AI Factory

#46

Post by low_common »

simonw wrote: post #28

My hunch is that this article is going to be almost completely impenetrable to people who haven't yet had the "aha" moment with Claude Code. That's the moment when you let "claude --dangerously-skip-permissions" go to work on a difficult problem and watch it crunch away by itself for a couple of minutes running a bewildering array of tools until the problem is fixed. I had it compile, run and debug a Mandelbrot fract…

That's a pretty trivial example for one of these IDEs to knock out. Assembly is certainly in their training sets, and obviously docker is too. I've watched cursor absolutely run amok when I let it play around in some of my codebase.

I'm bullish it'll get there sooner rather than later, but we're not there yet.

Re: Building a Personal AI Factory

#47

Post by tranchebald »

gerdesj wrote: post #33

"Here’s the secret sauce: iterate the inputs": No it isn't. There are no short cuts to ... anything. You expend a lot of input for a lot of output and I'm not too sure you understand why. "Example: an agent once wrote code ..." - not exactly world beating. If you believe this will take over the world, then go full on startup. YC is your oyster. I've run my own firm for 25 years. Nothing exciting and certainly not YC…

You come across as a massive hater. Maybe it’s a cultural thing. Do you actually have employees?

Re: Building a Personal AI Factory

#48

Post by rolha-capoeira »

marviel wrote: post #20

Thanks for the writeup! I talked about a similar, but slightly simpler workflow in my post on "Vibe Specs". https://lukebechtel.com/blog/vibe-speccing I use these rules in all my codebases now. They essentially cause the AI to do two things differently: (1) ask me questions first (2) Create a `spec.md` doc, before writing any code. Seems not too dissimilar from yours, but I limit it to a single LLM

I guess a lot of us are trying this (naturally) as solo devs, where we can take an engineering-first mindset and build a machine or factory that spits out gizmos. I haven't gotten to the finish line, mostly because for me, the holy grail is code confidence via e2e tests that the agent generated (separately, not alongside the implementation).

Re: Building a Personal AI Factory

#49

Post by marviel »

rolha-capoeira wrote: post #48
marviel wrote: post #20

Thanks for the writeup! I talked about a similar, but slightly simpler workflow in my post on "Vibe Specs". https://lukebechtel.com/blog/vibe-speccing I use these rules in all my codebases now. They essentially cause the AI to do two things differently: (1) ask me questions first (2) Create a `spec.md` doc, before writing any code. Seems not too dissimilar from yours, but I limit it to a single LLM

I guess a lot of us are trying this (naturally) as solo devs, where we can take an engineering-first mindset and build a machine or factory that spits out gizmos. I haven't gotten to the finish line, mostly because for me, the holy grail is code confidence via e2e tests that the agent generated (separately, not alongside the implementation).

Totally. Yeah I think your approach is a solid take!

Re: Building a Personal AI Factory

#50

Post by swader999 »

pjm331 wrote: post #23
vFunct wrote: post #16

The issue I'm facing with multiple agents working on separate work trees is that each independent agent tends to have completely different ideas on absolutely every detail, leading to inconsistent user experience. For example, an agent working on the dashboard for the Documents portion of my project has a completely different idea from the agent working on the dashboard for the Design portion of my project. The desig…

I’ve had success with building the first version of a thing mostly by hand and then telling Claude code to look at it as an example of how to do things when building the next N of them

The things that work on a regular dev team translate well to the agentic mode.
Post reply on HN