I have been using this : https://magnitude.dev/ for a while now. Is it something similar you are doing? I would love to have something that would connect to my codex, Claude, and opencode subscription rather than having to make a new subscription.
I agree. I quit cursor and replaced it with conductor and a mix of Claude Code / Codex/ Copilot and i dont miss it as such. Maybe one day I will come back.
Once men turned their thinking over to machines in the hope that this would set them free.
But that only permitted other men with machines to enslave them.
Frank Herbert, Dune, 1965
Designed in the era of Use-maxing vs Status-maxing. I think modern cars are taking a lot of car experience out and putting in the phone experience in. My Maruti Suzuki 800 was such a fun car to drive. Easy to repair. Decently efficient. Repair manual was understandable.
The new electrics are great. But they are less of a car and more of a transportation technology.
DB is weird. They seem to make their own rules and then run the game and “dont tell the rules to anyone”. I was on my way to catch a flight from Munich to my home (Madrid). I didn’t knew that apparently at one point the train splits into two parts and the front part goes to the airport and the other part just goes to the nearby cattle farms and comes back in 3 hours.
Google Maps - No idea
Citymapper - what?
English announcement - nien.
Thanks to an old lady, who told me that i needed to switch coaches to go the airport. Madre mia!!
Interesting. Yes, the pro features seem to be just about ai these days. I used affinity’s indesign equivalent while at work and it was quite good. I wonder what the business model is? Same as figma a while back?
It is an interesting take. I teach programming to designers as a part of a course called "Emerging technologies". Although, it is fun to see what students create, but it is not fun to solve doubts. When you are teaching basics, the students would quickly fire up ChatGPT and make some slop up. In the end, I have to fix their codes. I think, the learning output is reduced as they have not written any code. I am genuinely concerned as an educator. One thing that is missing is differentiating AI output and understanding what to keep and what to ignore. The sheer "aesthetic" of it. I feel, many do not take time to develop this very "human" skill and become very output oriented from the very start. This, IMO, affects learning. These tools are also quite addictive due to the sense of 'manufactured' certainty they offer, which is something that hinders learning. What is the point of learning how to add when you have the cheatsheet next to you?
Beginner here, I sort for agree. I think these tools are good to make a few good demos and quickly sketch something but you hit the ceiling soon where every other thing you do needs more work. There a lot of tutorials online plus the promise of AI automation as the next "get rich quick" thing.
I am curious what is a good tool to build agents these days? I am checking out mastra, someone at the cafe told me about Inngest.. wondering what would you use?
TBH, it seems like a questionable way to spend EU money. Technically, it's fascinating, but unless it's part of a broader geopolitical or long-term interoperability strategy, it's hard to justify the costs.
In Spain, we already deal with both Iberian and standard gauges—trains like the Talgo models can change gauges with minimal delay. It's not seamless, but it works reasonably well. Spain also has the world's second largest high speed train network.
What the EU could really benefit from is greater support for small companies and independent freelancers who are driving innovation. Unfortunately, governments (Spain included) often treat them as revenue sources, with high taxes and complex regulations, while large corporations can navigate around much of that with ease.
Yay! I like Magic Patterns. It is more useful and accurate compared other tools. I have successfully been able to get some design ideas implemented in it. It seems to understand consistency more than other tools.
I thought about the same thing the other day, but most LLMs are unfortunately not trained on large Ruby on Rails codebases. If you ask Claude about the most preferred languages it can code, it would recommend using Python or Javascript.
Maybe DHH can sponsor fine-tuning a LLM with more ruby on rails data :P
meet.hn/city/es-Madrid
http://indiantinker.bearblog.dev