So that’s why I am getting clickbaity last sentences in every response now at ChatGPT.
Things like ”If you want, I can also show a very fast Photoshop-style trick in Krita that lets you drag-copy an area in one step (without copy/paste). It’s hidden but extremely useful.”
Every single chat now has it. Not only the conversational prompt with “I can continue talking about this”, but very clickbaity terms like: almost nobody knows about this, you will be surprised, all VIPs are now using this car, do you want to know which it is? Etc
One thing I am exploring is that, with LLM (and enough $ to pay the tokens) you can filter out offenses and hate speech in player communications.
All typed message is effectively translated by the LLM as “coach speech” and what is put in the UI is the LLM output. Sure, it is not exactly the player words and can get expensive, but I think it can be a good solution
A soccer web game where you are the coach and your only possible interaction is shouting (ie typing) messages to your players from the sidelines. An LLM interpret your messages and pass instructions into the game engine.
I built my share of AI stuff (although more using AI in the product than vibe coding ), so I won’t complain. But I did got frustrated when I recently posted a Show HN that I thought HN community would like and no one did.
It is a comeback from a post that stayed for a few hours in the front page a few years ago. Also, it is a useful, non-AI slop, free product. So when it got none upvotes it made me think how I don’t understand HN community anymore how I used to think I did.
Here is the post for the curious
Show HN: (the return of) Read The Count of Monte Cristo and others in your email
Sorry for the late reply, hope you still see this.
Yes, I went with Postgres to be safe. I am still serverless, but now there is Vercel doing a good job for serverless DB. They integrate with Neon, which makes Postgres serverless possible.
More things are into Vercel as well, as the cron jobs, which I used to use AWS only for that. Much easier now in configuration by code through Vercel.
Anything goes wrong with Vercel or Neon and I can just export my whole DB and go for a regular server anywhere.
I am also 45 and on a similar current situation as you (although I luckily come from a privileged background). One thing that is working a lot for me is trying to become a professional fiction writer.
There is a lot a of ambition and uncertainty in it. I always enjoyed writing (whatever the context, not only fiction) and now I enjoy getting better at writing fiction. I enjoy being part of a group of other wanna-be writers with the same goals and challenges. I made real friends this way. I enjoy listening podcasts, videos, interviews from experienced authors. I am even enjoying more working on some software side-projects that are related to literature (in general or my own).
At the same, there is very little chance that this endeavor will have any financial return. In Brazil, where I live, you can count in the dozens the number of writers that live solely from the income of book royalties and in the hundreds the number of writers that live from literature (royalties + workshops, online courses, literary services, etc).
So, even some successful authors that have decent number of readers (for Brazil's context) and some awards, have a day job.
This, interestingly for me, who has a well-paid job, removes the pressure of this project of mine. Since it is an art project, to not have the pressure of needing to earn money, actually makes my art better, I have more patience and time to reflect upon it (ironically, increasing my chances to earn money through my art).
But I still have the pressure to earn readers. It's not like I am painting paintings that I am happy enough to complete and leave them on my house studio. I am not doing art for myself, but for others. That's where the ambition part come from. Which I like.
I don't think this comes from a mid-life crisis, as I write short stories since my twenties. It's only now that I have the time, money, and, I might say, wisdom to be able to do it seriously. Writing is one form of art that benefits a lot from like experience.
Just to share what worked for me, and maybe you can find something for you that fits the bill of being an ambitious project that you hope to achieve something meaningful from, but that it's not necessarily attached to financial outcomes. The privilege of being able to be professional about something that might not return more money, even if successful, is something that I treasure a lot.
The OP and your comment just made me cancel my Milanote subscription, export all my notes to markdown and start using Obsidian (to later experiment with this Reor).
As a side-effect, I just noticed that I prefer a long markdown file with proper headings (and an outline on the side) than Milanote's board view, which initially felt like a more free form better suited for unorganized thoughts and ideas for writing that I had (I use it for my fiction writing).
I still can have documents as a list of loose thoughts, but once I am ready to organize my ideas, I just use well written and organized headers, edit the content and now I have a really useful view of my idea.
Not as professional (or useful) as the ones in this list, but I created a small neat project using generative AI that I find pretty fun -- an acrostic generator.
I don't think they ever meant it's impossible to get there, just unnecessarily difficult (or expensive) due to a regulation that is bring unnecessary hassle (which is exactly what you are describing, but, somehow, using a tone that it's something smooth).
I completed the technical prescreen and never got an answer. Not even a rejection. Also, emailed the poster on last month thread and still no response.
I may be wrong here, but I think there is a regulation that prevents the owner of an airline from piloting the planes of their own airline. It might create a conflict of interest between saving money and being cautious.
This is not only a theoretical risk. It happened. A Brazilian soccer team, Chapecoense, hired a private airliner to get them from Bolivia to Colombia. Due to some bad luck, airport closing hours and whatnot, the flight plan had to be changed and the plane was fueled below what the regulations required. They were getting close to the destination airport when they got a low fuel warning. More bad luck and in the airport of the destination the flight control asked their flight to wait while another plane had priority in landing.
There were alternatives to redirect the flight or request priority to land, which they only requested when it was too late and the plane crashed due to fuel exhaustion. 71 of 77 people in the plane died in the crash, including the pilot.
The pilot was also the co-owner of the airline, so there is room to speculate that he didn't want to promptly admit to be low on fuel and require priority to land, or divert to another airport when the low-fuel warning appeared, because he would have to admit that he fueled below what the regulations asked. He could face the consequences, like a fine or losing his license.