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

You just described one minor use case of the tools and claim it's not needed anymore

It's like saying cars are obsolete now because you only used yours to go to the church and use your bike for that now

Don't know about Postman, but Bruno has much more to offer. In our team we use an exported shared collection (stored in github) of all the extensive APIs of all the apps we share or even those we just use so that anyone can just import that and use them


I do not claim it's not needed anymore

This is awesome, why did I just learn about this! Gonna add these all over my homelab


I don't necessarily disagree with this post but I really disagree with how it is written and with the contempt it expresses towards a fellow tech guy.

First of all - after reading all that, I still don't fully know what the author exactly means by "software factory". Please define the term if you are to argue about it so we know exactly what you're talking about.

Second of all - the author is glorifying one approach to tech (the "idea guys") and severely downplaying other approaches. Just because he finds this fun and entertaining doesn't mean everyone does - and the world needs all of those people. Idea guys are cool and they just got a very powerful tool, but we still need those passionate devs who dedicate a lot of their time to building and researching massive projects even if they're not sure they make sense


>I don't necessarily disagree with this post but I really disagree with how it is written and with the contempt it expresses towards a fellow tech guy.

It's the same "look at how right I am" post we've all read dozens of times. Dismissive and condescending about what projects should or shouldn't be explored, and of the people who explore the wrong ideas. Same as always, just with a fresh coat of paint for the AI age.

I have thoughts on what may be fruitful and worthwhile to explore. But this post isn't about that, really.


My only guess is a software factory is like a boilerplate starting point and I'm still not sure


I don't think we should even be talking about the software factory anymore.

For home stuff I've shifted to a software day spa

But for work, I've gone a step further and now run a software CPG distribution center combined with a software recycling plant.

The code flows out of the DC, gets consumed by the business and then tossed back to the recycling plant, fully green from a 1's and 0's perspective.


what immediately came to mind for me is something like gastown. If that is the case I think I'd agree with the auther and a parallel from pre-AI would be "using kubernetes for personal projects is a waste of time" - so much time and resources spent on something that is way overkill and in many ways just would get in the way of just shipping something, anything and then going from there.


Sorry but this is such a manager thing to say. "Everything is replaceble by AI except what I do! - make decisions"

I don't find that true at all. We even have an LLM specialized in exactly that - making decisions

What I would agree on that LLMs maybe possibly will not replace us at that soon is "noodling" - just letting your thoughts wander around an idea, trying to come up with some cool and unique. Someone will probably run a bunch of agents soon and prove me wrong on this though


> this is such a manager thing to say

This is slightly amusing given that I am a solo founder running a solo SaaS business :-)


Are you using the API or is it self hosted as well?

(sorry if this question doesn't make sense)


It is self hosted.

Ollama serves models on an OpenAI compatible API directly on the inference machine, which most open source harness software will connect to. The inference machine has a name like inferencemachine.local on my home network so the Ollama URL looks like http://inference machine:11434/v1 to connect to any model I've downloaded.


> AI agent on my phone I can long-press power button and give spoken commands ("add milk to the shopping list"). Uses private home inference machine, see below.

For this part, are you using a tool-calling harness like Pi or Codex? Or did you sort of hack it together with prompts that tell it what json to emit?

I just got the rest of the “application layer” for my setup working yesterday, with a small set of evals. Auto-filing voice notes is what’s next for me.


The harness is using my own project "runprompt" which you can find here:

https://github.com/chr15m/runprompt

That has a bunch of Python tools for things like adding to TODO list, notes, looking stuff up, etc.


Generate and dump on others to verify is how the generative-AI people operate. Be it in maths or just your regular job.

The amount of Confluence pages of "research" that is just a dump of LLM output someone passed to me to review is staggering

I hate this approach, it's unbelievably selfish


That's the way to go. Anyone who publishes any of their work in the open web and who values what they are doing should do whatever possible to block the AI scrapers (which is often difficult or impossible, I know) until all that's left for them to feed on is their own garbage.

Let the garbage-spewing machines choke on their own garbage


Allowing someone to create my persona which they control sounds like a fever nightmare to me. I'm not touching this with a stick until I can host it - and control it - myself


Yeah it kinda feels like a great, original meal but served on plasticware


People don't like reading articles "redacted" by AI because that feels disrespectful

Imagine approaching someone you wanna talk to and they just silently point to their assistant, suggesting you talk to them instead. I want to hear your thoughts from you, not filtered by some assistant/machine


Im not sure if Im being an idiot but I thought it would be LESS offensive


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

Search: