Hacker Newsnew | past | comments | ask | show | jobs | submit | danfunk's commentslogin

I love "small internet theory." Beautiful view of the future.


You may have said it better than I, in shorter words. An LLM in the hands of someone with expertise is life changing, and in the hands of someone without it - it's a bit dangerous, but also wonderfully empowering, even if they can't make a good chair on their first try.


This matches my experience exactly. I came back to coding after 20 years away — the expertise I brought wasn't Go syntax, it was product thinking and architectural discipline from years of project management. That turned out to be exactly what the AI needed to produce something coherent and maintainable. The tool amplified what I already knew, not what I didn't.


Spent a delightful weekend in Quebec last month. Beautiful city, great culture, friendly people, best damn duck I have ever eaten in the a resteraunt they must having teleported from southern France


Great tool for a Makerspace - really appreciate the ability to use the same tool for laser cutting, 3d printing, and CNC. These are big jumps for people typically - having a familiar tool would help people transition from one area to another.


Makerspaces and education are two areas of focus. no SW install, fully loads in under a second. through the Onshape integration and ability to run on Chromebooks, it's made its way into high school and university STEM curriculum.


What brings me back to hacker news are these posts that ask questions yanked unexpectedly directly from my own soul, in words more articulate than I could manage. And then somehow manages to answer those questions. Thank you.


12 years ago I got divorsed. My wife and I had a company together, and she kept the company. I hadn't spent time with family in years, had few friends outside of work. I did independent contract work out of my house. Deeply isolated times, interspersed with part time custody of my son. I ended up starting a Makerspace , renting a building and setting up a 3d printer. That was all 11 years ago. We now have 6k square foot building, 8 different guilds, from pottery to black smithing. I count myself beyond lucky for the community. Like the author, I sent too many years discounting the most important part of life .. Our relationship with other humans.


That's a really interesting story. Did you really start it with just a single 3D printer? I thought about doing this a few times.

I don't necessarily need it for the social aspect (although I love meeting people), my work has me engaging with people all the time and travelling nationally and internationally 6+ times per year.

In my case, if I had to identify motivation, I would say that I have an interest in attempting to recreate the experience I had for many years as a mentor for our local FRC (high school robotics competition) at an adult level. The other motivation is this idea I have that retirement should not be a passive experience where you go from having a mission and work every day to watching TV and fishing with no purpose in life. I have seen how the latter degrades people and I have zero interest in being a part of that club. I can see a maker space potentially being a way to continue to socialize at some level (even if most of it is somewhat transactional and superficial) and keep busy physically and intellectually.

I own a lot of interesting manufacturing equipment, from multiple 3D printers all the way up to a full Haas industrial CNC vertical machining center, welding, manual machining, etc. In other words, if I contribute all of this hardware, I could start a pretty nice maker space with almost zero investment in tools.

Curious about your experience and, in particular, if there are any negative aspects that you might want to warn against.


Same experience with Google. I was setting up SSO for a new web application and set off some AI flag on a sub domain for our company website. For 2 weeks every visitor saw a warning that out site was a phishing scam. Nightmare. With no recourse. No number to call. No person to talk to. No actual explanation of the error (I still don't know exactly what I got wrong). I just took it down, waited, and prayed.


All these comments are from the standpoint of being managed, with a derogatory view of someone who would stoop so low as to take a management role. I liked the article. Managing people is ass hard. Doing so is a way to make peoples working lives better, anf to tackle problems larger than a single person can accomplish. Thinking about how to do it better is good thing. It takes courage.


I think this is the attitude that most people take issue with that this comment represents.

So please tell us why we are wrong? Because I can just go and claim in the same vein of your comment to say: "Managing people is easy peasy"


I hate web forms. You hate web forms. Especially when when they are long. Or one form follows another after another after another.

We have conversational LLM's that can make this feel much better, and there is this great BPMN diagramming tool that makes it easy to describe the flow of long, complex sessions like these. Together they can give everyone a far better experience.

There is a companion video and a working demo - where you can run the model, change it, and refine it to cover new topics or extend the conversation.

We are really excited about this technique and look forward to your feedback.


We are working on a workflow engine as well - picking up concepts from the past - not quite as far back as mainframes, but I respect looking back to the past for things that work well, and re-applying them to a new world. I'd be up for sharing notes. Our work is here https://github.com/sartography/spiff-arena -- live demo is here https://spiff.works/agent-demo


Hi, thank you for your feedback.

I think in the past, I've already had a look at your repo, but it's a little bit different from my idea. Your is build around BPMN (and, if I'm not wrong, it's basically a easy way to create custom finite state machines) while I'm working on a "lower level".

I have 3 concepts: tasks, links and workflows(a collection of tasks). Links can be created between task of the same workflow or task from different workflows. Workflows can be scheduled based on calendar rules(cron like or "2nd working day of the month" and similar) or external events(api call, new file on s3, ecc ecc). Normally workflows are DAGs, but loops can be created if needed.

The other idea is that it's just the orchestration layer, the task needs to be executed by specific "agent", that can be written in any language (there is a very simple protocol build on top of http to get the tasks from the orchestrator or to send the results) and can be installed on local or remote server.

Just some context: in the mainframe era, businesses used to be orchestrated by a unique "scheduler" running all day long(it was so flexible that basically any business from banking to insurance to manufacturing to industry were able to adapt it to their needs). Bigger companies used to have >100k (or even millions) of tasks per day with very well-defined dependencies. The "good" part was that it was very easy to monitor and manage your batch operations. My idea is to reproduce something similar, but also to add a better support for distributed envs and "human" tasks.


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

Search: