I think it highly depends on your perception on what is your job.
If programmer is only the code-writer - then it is reasonable to agree with the post.
If on the other hand the developer is problem solver - well it just changes what problems you're solving. Somehow I don't see the future where CEO of any respectable company would sit with AI and ask Agent to develop features. You hire people who solves problems for you.
Facing similar issue with monitoring part of executions. What is your solution if I may as - have you taken smth of the shelf and extended to your needs or did you built from the ground up everything?
Honestly we were looking at hatchet / pickaxe - similar vein of a project but more dev focused, but in the end realised our use cases were not all that complex so just built everything in a bespoke manner.
We used n8n for two things mostly - AI agents and process automation.
For AI we just built own MCP servers, and then the agents are quite easy to use as the major frameworks kinda help you with it. N8N’s AI is kinda just a UI layer for langchain - though we just used google’s adk.
For process automation - well there is so much options it’s not even funny.
While it's definitely interesting comparison, I would say the that key thing is that genius is limited in scope. What I mean by that is given any single genius - we might agree that he is one on subject X but not on subject Y.
With AGI it seems that expectation is to cover all the subjects. Which I think is more like god. You either believe it or you don't. Noone have definite proof of its existence or non-existence.
I actually built the app myself. And for one simple reason - recently started learning to better plan my time. Started with paper version, and up to 5 most important task - my personal goal is to have consistency rather than squeeze every minute of every day.
And paper version is great. However, the vacation came and I wasn't really keen on dragging the book everywhere. Additionally i noticed that while planning, I don't really respect my long term goals - so I build an app for that: Simple thing that does several thing:
- 1. Keep only 5 slots for most important tasks.
- 2. Have calendar view in the same view (like google tasks) to make sure that I havent' forgotten some important meeting
- 3. (Unlike google tasks, or clickup) - have short-term and long term goals in the same view , to make sure that every important task is related to long term goal
- Bonus: I see stats on how much of important tasks I have completed. Goal is at least 80% avg for 7 days.
- Bonus2: I've added my values to make sure that these are not forgotten in other places.
So single view to address todays work and relate it to long term vision. But I believe it depend on what you're optimising for. Dumping things or makeing sure that signal to noise ratio is better.
I'm reading this and kind of stuck on the 4th. I have a printer though not much of 3D designer. How do one get 3D models for parts that is suitable with SparkFun electronics?
For electronics, all you really need to get started is an Arduino, 3 hobby servos, and a breadboard and wires. The first robot I sold was basically just that. And the physical parts were Lego-Technic compatible laser-cut (later 3D printed) beams. (https://bitbeam.org/, https://www.thingiverse.com/thing:11747)
Start making your own "lego" then go from there. This idea can get you pretty far --> https://bitbeam.cc/en/
How do you protect agains "professionals" abusing the system. So maybe thats not relevant in USA but I see potential in our communities that smaller repair shops or construction contractor would come and use tools disproportionally to their input. That's especially relevant with consummable parts like blades, files, etc
I do a lot of diy, jobs on the side for friends and I know a handful of professional tradies.
None of them would want to not own tools they use even semi regularly and for insurance purposes (and peace of mind) they would almost certainly have to hire tools they don’t own from a rental company and they will just pass the rental cost on to the client.
Absolutely, it’s not for everyone. Tool libraries aren’t meant to replace pro setups. I think they’re more for casual DIYers, for occasional project, or people who don’t want to buy something they’lll only use once or try a new tool before buying.
A professional usually needs a tool when they need it and can't rely on the vagaries of availability at a library. And it's easy to kick out someone who checks out a tool all year.
Most consumable parts can be excluded from lending. Batteries are trickier.
You're totally right! I agree that batteries are also trickier but we're working on fixing this. If you have any ideas or thoughts, feel free to contact me at julien@patio.so
Yeah, that can happen. Having some basic rules and keeping an eye on things usually helps. People are often asked to bring or replace their own consumables too.
What I see LLMs at this point is simplified input and output solutions with reduced barriers of entry. So application could become more widespread.
Now that I think of it, maybe this AI era is not electricity, but rather GUI - like the time when Jobs(or whoever) figured out and adopted modern GUI on computers allowing more widespread uses of computer
Do they only have reduced barriers of entry if you aren't fussed about the accuracy of the output? If you care that everything works correctly and is factually correct, do you not need the same competency as just doing the task by hand.
It's a good analogy because the key development does seem to have been the interface. Instead of wrapping it up as a text autocomplete (a la google search), openai wrapped it up as an IM client, and we were off to the races.
I quite liked the video. Hope you get to launch the product and I could try it out some day.
The only thing that I kept thinking about was - if there is a correction needed- you have to make it fully by hand. Find everything and map. However, if the first try was way off , I would like to enter from "midpoint" a correction that I want. So instead of fixing 50%, I would be left with maybe 10 or 20. Don't know if you get what I mean.
Yes, the idea is to ‘speak/write’ to the local model to fix those little things so you don’t have to do them by hand. I actually already have a fine-tuned Qwen model running on Apple’s MLX to handle some of that, but given the hard YC deadline, it didn’t make it into the demo.
Eventually, you’d say, ‘add an additional layer, TopicsController, between those two files,’ and the local model would do it quickly without a problem, since it doesn’t involve complicated code generation. You’d only use powerful remote models at the end.
Can I ask you why so many things with N8N is connected over Telegram it seems versus for example slack? Not a user of Telegram so I honestly am curious about this choice
Personally I hate Slack, it never works on my PC because of their organizations/workspace system, where you need a separate account for each community you are in. Also, it's really buggy and login often doesn't work, or switching accounts breaks things.
Telegram has a really good mobile app, and their BotFather makes it easy to create custom integrations. They display nicely a lot of notification formats (text/html/markdown) and it's free.
Slack is too bloated to simply use for notifications.
I can only talk about the Slack integration story since I never worked with the Telegram API, but over the last couple of years it has become an incredible mess. There are various ways to do the same thing, different permission models, deprecated endpoints without clear alternatives... It has become a pain honestly.
I think many users choose Telegram, as it's really simple. Slack is usually slightly more work to setup, e.g. creating the slack bot for it. I'm using Slack ware more than telegram, but I guess both work.
I have similar thoughts and I have come to conclusion that that's the beauty and the curse of this technology. If one relies too much on it - it's gonna be a curse. However, if technology is used with care - it's a beauty. Not only does it keep SWE jobs "secure" - it really helps a lot for those who know what they are doing.
I think in the end AI will be more advanced tool, but a tool nonetheless. Like methodologies and principles, good practises etc. - they only work if you use it with care and added thought and adaptation to your case. DRY it a great principle. But sometimes it's better if you repeat yourself. For one reason or another. And these are the the tradeoffs that human in the loop should be making imho.
> I have similar thoughts and I have come to conclusion that that's the beauty and the curse of this technology.
I agree. When I read these articles on vibe coding I can't help to think that these guys are basking in the glory of the impressive maze they built around themselves. Of course running these things in production and having them reach the state of legacy code is an entirely different thing. Building a maze is one thing, having to run around it is an entirely different challenge.
It's like one of those world expos: everything looks fantastic, but the moment the event ends everything just crumbles.
If programmer is only the code-writer - then it is reasonable to agree with the post.
If on the other hand the developer is problem solver - well it just changes what problems you're solving. Somehow I don't see the future where CEO of any respectable company would sit with AI and ask Agent to develop features. You hire people who solves problems for you.