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

21–30 of 167 posts

Re: Building a Personal AI Factory

#21

Post by conradev »

schmookeeg wrote: post #17
steveklabnik wrote: post #3

I'd love to see more specifics here, that is, how Claude and o3 talk to each other, an example session, etc.

I use Zen MCP and OpenRouter. Every once in awhile, my instance of claude code will "phone a friend" and use Gemini for a code review. Often unprompted, sometimes me asking for "analysis" or "ultrathink" about a thorny feature when I doubt the proposed implementation will work out or cause footguns. It's wild to see in action when it's unprompted. For planning, I usually do a trip out to Gemini to check our work, off…

proof -> show the code if you can!

Then engineers can judge for themselves

Re: Building a Personal AI Factory

#22

Post by kasey_junk »

photon_garden wrote: post #9

It’s hard to evaluate setups like this without knowing how the resulting code is being used. Standalone vibe coded apps for personal use? Pretty easy to believe. Writing high quality code in a complex production system? Much harder to believe.

I don’t really understand this article or the workflow it’s describing as it’s kind of vague.

But I use multiple agents talking to each other, async agents, git work trees etc on complex production systems as my day to day workflow. I wouldn’t say I go so far as to never change the outputs but I certainly view it as signal when I don’t get the outputs I want that I need to work on my workflow.

Re: Building a Personal AI Factory

#23

Post by pjm331 »

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

Re: Building a Personal AI Factory

#24

Post by ozten »

jwpapi wrote: post #13
ClawsOnPaws wrote: post #10

Earlier quoted context omitted.

I keep coming to the same conclusion, which basically is: if I had an LLM write it for me, I just don't care about it. There are 2 projects out of the maybe 50 or so that are LLM generated, and even for those two I cared enough to make changes myself without an LLM. The rest just sit there because one day I thought huh wouldn't it be neat if, and then realized actually I cared more about having that thought than havi…

I’ve written a full stack monorepo with over 1,000 files alone now. I’ve started with AI doing a lot of the work, but the percentage goes down and down. For me a good codebase is not about how much you’ve written, but about how it’s architectured. I want to have an app that has the best possible user and dev experience meaning its easy to maintain and easy to extend. This is achieved by making code easy to understand…

What does the full stack monorepo do?

Re: Building a Personal AI Factory

#25

Post by schmookeeg »

conradev wrote: post #21
schmookeeg wrote: post #17

Earlier quoted context omitted.

I use Zen MCP and OpenRouter. Every once in awhile, my instance of claude code will "phone a friend" and use Gemini for a code review. Often unprompted, sometimes me asking for "analysis" or "ultrathink" about a thorny feature when I doubt the proposed implementation will work out or cause footguns. It's wild to see in action when it's unprompted. For planning, I usually do a trip out to Gemini to check our work, off…

proof -> show the code if you can! Then engineers can judge for themselves

Yeahhhhhh I've been to enough code reviews / PR reviews to know this will result in 100 opinions about what color the drapes should be and what a catastrophe we've vibe coded for ourselves. If I shoot something to GH I'll highlight it for others, but nothing yet. I can appreciate this makes me look like I'm shilling.

It makes usable code for my projects. It often gets into the weeds and makes weird tesseracts of nonsense that I need to discover, tear down, and re-prompt it to not do that again.

It's cheap or free to try. It saves me time, particularly in languages I am not used to daily driving. Funnily enough, I get madder when I have it write ts/py/sql code since I'm most conversant in those, but for fringe stuff that I find tedious like AWS config and tests -- it mostly just works.

Will it rot my brain? Maybe? If this thing turns me from an engineer to a PM, well, I'll have nobody to blame but myself as I irritate other engineers and demand they fibonacci-size underdefined jira tix. :D

I think there's going to be a lot of momentum in this direction in the coming year. I'm fortunate that my clients embrace this stuff and we all look for the same hallucinations in the codebase and shut them down and laugh together, but I worry that I'm not exactly justifying my rate by being an LLM babysitter.

Re: Building a Personal AI Factory

#26

Post by steveklabnik »

schmookeeg wrote: post #17
steveklabnik wrote: post #3

I'd love to see more specifics here, that is, how Claude and o3 talk to each other, an example session, etc.

I use Zen MCP and OpenRouter. Every once in awhile, my instance of claude code will "phone a friend" and use Gemini for a code review. Often unprompted, sometimes me asking for "analysis" or "ultrathink" about a thorny feature when I doubt the proposed implementation will work out or cause footguns. It's wild to see in action when it's unprompted. For planning, I usually do a trip out to Gemini to check our work, off…

It’s not about proof: it’s that at this point I’m a fairly heavy Claude Code user and I’d like to up my game, but I’m also not so up on many of these details that I can just figure out how to give this a try just from the description of it. I’m already doing plan-up-front workflows with just Claude, but haven’t figured out some of this more advanced stuff.

I have two MCPs installed (playwright and context7) but it never seems like Claude decides to reach for them on its own.

I definitely appreciate why you’re not posting code, as you said in another comment.

Re: Building a Personal AI Factory

#27

Post by simonw »

steveklabnik wrote: post #8
skybrian wrote: post #4

> It’s essentially free to fire off a dozen attempts at a task - so I do. What sort of subscription plan is that?

Claude Code's $200 Max subscription can take a lot of usage. I haven't done a dozen things at once, but I have worked on two side projects simultaneously with it before. ccusage shows me getting over 10x the value of paying via API tokens this month so far...

I had to look that up: https://github.com/ryoppippi/ccusage

  npx ccusage@latest
Outputs a table of your token usage over the last few days, which it reads from the jsonl files that Claude Code leaves tucked away in the ~/.claude/ directory.

Re: Building a Personal AI Factory

#28

Post by simonw »

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 fractal generator in 486 assembly today, executing in Docker on my Mac, just to see how well it could do. It did great! https://gist.github.com/simonw/ba1e9fa26fc8af08934d7bc0805b9...

Re: Building a Personal AI Factory

#29

Post by steveklabnik »

simonw wrote: post #27
steveklabnik wrote: post #8

Earlier quoted context omitted.

Claude Code's $200 Max subscription can take a lot of usage. I haven't done a dozen things at once, but I have worked on two side projects simultaneously with it before. ccusage shows me getting over 10x the value of paying via API tokens this month so far...

I had to look that up: https://github.com/ryoppippi/ccusage npx ccusage@latest Outputs a table of your token usage over the last few days, which it reads from the jsonl files that Claude Code leaves tucked away in the ~/.claude/ directory.

Don’t sleep on the other options either, the live updates are cool, see where you’re at in the five hour session.

Re: Building a Personal AI Factory

#30

Post by dkdcio »

I went down this (and even built a bit of internal web tooling) —- it’s like playing multiple games of online poker for me (instead of the factoria analogy here)

it’s really promising, but I found focusing on a single task and doing it well is still more efficient for now. excited for where this goes

Post reply on HN