[HN Gopher] Building a Personal AI Factory
       ___________________________________________________________________
        
       Building a Personal AI Factory
        
       Author : derek
       Score  : 31 points
       Date   : 2025-07-01 21:14 UTC (1 hours ago)
        
 (HTM) web link (www.john-rush.com)
 (TXT) w3m dump (www.john-rush.com)
        
       | IncreasePosts wrote:
       | Okay, what is he actually building with this?
       | 
       | I have a problem where half the times I see people talking about
       | their AI workflow, I can't tell if they are talking about some
       | kind of dream workflow that they have, or something they're
       | actually using productively
        
         | ClawsOnPaws wrote:
         | 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 having the
         | result of that thought. Then you end up fighting with different
         | models and implementation details and then it messes up
         | something and you go back and forth about how you actually want
         | it to work, and somehow this is so much more draining and
         | exhausting than just getting the work done manually with some
         | slight completion help perhaps, maybe a little bit of
         | boilerplate fill-in. And yes, this is after writing extensive
         | design docs, then having some reasoning LLM figure out the
         | tasks that need to be completed, then having some models talk
         | back and forth about what needs to happen and while it's
         | happening, and then I spent a whole lot of money on what
         | exactly? Questionably working software that kinda sorta does
         | what I wanted it to do? If I have a clear idea, or an existing
         | codebase, if I end up guiding it along, agents and stuff are
         | pretty cool I guess. But vibe coding? Maybe I'm in the minority
         | here but as soon as it's a non trivial app, not just a random
         | small script or bespoke app kind of deal, it's not fun, I often
         | don't get the results I actually wanted out of it even if I
         | tried to be as specific as I wanted with my prompting and
         | design docs and example data and all that, it's expensive, code
         | is still messy as heck, and at the end I feel like I just spent
         | a whole lot of time actually literally arguing with my
         | computer. Why would I want to do that?
        
           | jwpapi wrote:
           | 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, for yourself, for others.
           | 
           | In my case it's more like developing a mindset building a
           | framework than to push feature after feature. I would think
           | it's like that for most companies. You can get an unpolished
           | version of most apps easily, but polishing takes 3-5x the
           | time.
           | 
           | Lets not talk about development robustness, backend security
           | etc etc. Like AI has just way too many slippages for me in
           | these cases.
           | 
           | However I would still consider myself a heavy AI user, but I
           | mainly use it to discuss plans,(what google used to be) or to
           | check it if I've forgotten anything.
           | 
           | For most features in my app I'm faster typing it out exactly
           | the way I want it. (with a bit of auto-complete) The whole
           | brain-coordination works better.
           | 
           | I guess long talk, but you're not alone trust your instinct.
           | You don't seem narrow minded.
        
       | steveklabnik wrote:
       | I'd love to see more specifics here, that is, how Claude and o3
       | talk to each other, an example session, etc.
        
         | breckenedge wrote:
         | I presume via Goose via MCP in Claude Code:
         | 
         | > I also have a local mcp which runs Goose and o3.
        
           | steveklabnik wrote:
           | Ah, I skimmed the docs for Goose but I couldn't figure out
           | exactly what it is that it _does_ , which is a common issue
           | for docs.
           | 
           | For example:
           | https://block.github.io/goose/docs/category/tutorials/ I just
           | want to see an example workflow before I set this up in CI or
           | build a custom extension to it!
        
             | breckenedge wrote:
             | Classic Steve Klabnik comment.
        
         | web3aj wrote:
         | +1
        
         | schmookeeg wrote:
         | 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, offer ideas, research, and ratings of completeness. The
         | iterations seem to be helpful, at least to me.
         | 
         | Everyone in these sorta threads asks for "proofs" and I don't
         | really know what to offer. It's like 4 cents for a second
         | opinion on what claude's planning has cooked up, and the
         | detailed response has been interesting.
         | 
         | I loaded 10 bucks onto OpenRouter last month and I think I've
         | pulled it down by like 50 cents. Meanwhile I'm on Claude Max @
         | $200/mo and GPT Plus for another $20. The OpenRouter stuff
         | seems like less than couch change.
         | 
         | $0.02 :D
        
       | skybrian wrote:
       | > It's essentially free to fire off a dozen attempts at a task -
       | so I do.
       | 
       | What sort of subscription plan is that?
        
         | steveklabnik wrote:
         | 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...
        
       | photon_garden wrote:
       | 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.
        
       | solomonb wrote:
       | > When something goes wrong, I don't hand-patch the generated
       | code. I don't argue with claude. Instead, I adjust the plan, the
       | prompts, or the agent mix so the next run is correct by
       | construction.
       | 
       | I don't think "correct by construction" means what OP thinks it
       | means.
        
         | btbuildem wrote:
         | Also, aren't they just rolling the dice here? Can you turn down
         | the temperature via Claude Code?
        
       | vFunct wrote:
       | 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 things that aren't in the
       | instructions. 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 design consistency is not there, not
       | just visually, but architecturally. Database schema ideas are
       | inconsistent, for example.
       | 
       | You start to update instruction files to get things consistent,
       | but then these end up being thousands of lines on a large project
       | just to get the foundations right, eating into the context
       | window.
       | 
       | I think ultimately we might need smaller language models trained
       | on certain rules & schemas only, instead of on the universe of
       | ideas that a prompt could result in.
        
       ___________________________________________________________________
       (page generated 2025-07-01 23:00 UTC)