melvinroest

I knew it! Those 30 and 40 somethings are always up to something. You never see them, never hear them, but here they are slowing their cognitive decline. They are clever little rascals. They're just like the species they're watching.

But I created a set of amazing binoculars with automatic AI age detection via radar for the small friendly price of 39.49$. Looking for a bird watcher? Get the SilentBirdWatchDectector 3000 and slow your cognitive decline at double the rate.

Don't watch the birds, watch the bird watchers instead. They may do something interesting.

(I'll see myself out...)

I've been saying this as well. I've also been borrowing from the Smalltalkers by using the words moldable development. In my opinion, vibecoding an application is a good way to do requirements engineering. You constantly talk to users and create a new app every day (or every 2 days) and see how they react. When you see that your users are delighted with your app and your experts claim the app delivers real value, then the prototyped application becomes the spec.

So I find the whole spec-driven development hype odd. I much rather vibe code an app, use that as a spec and then start anew to create the real thing. I haven't fully figured out yet what the best mode is there. So far I'm mostly hand coding it, thinking a lot about trade offs and I have an LLM read the full codebase of the vibe coded prototype and what I'm hand coding, so that I can ask very specific questions about how certain data flows or certain small things that I'm missing.

To me, this way of working is working great. You go from proving that an app provides value to your users through vibecoding through then productionizing it so you can capture all the users that this would be valuable to. It is of course important to sample your users correctly, such that they are a representative sample of your user population but since I do this within organizations usually and the apps are internal, that's usually an easy thing to do.

I didn't have that but I instead did a lot of music production as a teenager, hand dragging midi notes. It turns out, I have perfect pitch. But I learned that at 27 where a musically trained person noticed it. I make melodies all the time in my head.

It was a funny moment where she was like "you have perfect pitch!" "What is perfect pitch?"

I guess it's a shame, I could've been a great musician if I was trained.

In any case, if you want to meet up online, my email is in my profile. You sound fun!

On the one hand yea, but on the other hand, society is trying to create a situation where the biggest necessities are less of a burden. The big 4 IMO are: food, water, air, sleep. I get water out of the tap. It costs a lot less for me to get clean water than it is costing people 500 years ago (on average). At least that's my guess anyway.

I beatbox and sometimes I sing. Though to be fair I am just being me. While I do have musical ability, I don't use that to impress people. It's a me thing. It keeps my brain juice flowing.

Knowing English as a second language and Dutch as a first language is different than knowing, for example, Dutch as a second language and English as a first.

I know people in both camps. I have more respect for English speakers learning Dutch than for Dutch speakers learning English. Even though I respect both. But the simple truth is: there's a lot of incentive to learn English. There is not a lot of incentive to learn Dutch.

Why Norwegian? Why not Luxembourgish then?

Yea I say something similar. LLMs have a tendency to add, because there are many more tokens than a stop token. They can remove, they can edit, but their bias is to add. My suspicion is that training them when to stop when it is best to stop is harder than training them to make a plausible sounding story.

Isn't the author of The Culture series an interesting answer to this? I only read The Player of Games. To me it was fun to read that you could just play games your whole life.

I have a bit of both. Most of my thoughts aren't really originally because I'm not playing around and go wild. This is what LLMs seem to be lacking a bit.

Most of my thoughts are things that other people have come up with as well. Aka it feels like I'm just predicting the next token based on the data that I already have.

It's only when I go to places such as "what if life at the speed of light is possible, what would that look like?" that I get to places I personally find somewhat novel. It's almost a different dimension for these guys of course since a million years can feel like 10 years to them. Yet, they're moving so fast, but time-wise they move so slow, maybe even too slow for us to understand that anything can be alive at that speed (I'm not claiming there's life at light speed by the way, I just think it's fun to imagine that there is).

What kind of skills?

My message to the world is that LLMs should be able to point anything they see in the application they're in or even the whole computer (if you give it that kind of access).

For web apps, WebMCP is a way where you can make a frontend way more discoverable to an LLM rather than that it is going to read all your code. I sometimes create this in my apps at home and sometimes in my apps at work and it makes LLM assistants way more usable. It also helps if they can highlight certain things of a visual.

We humans can do this too on paper. We can point at something, we can highlight something with a marker. Why not give an LLM these capabilities as well?

> Personally I solved this problem for myself by moving away from the country.

Quite drastic to move away from a country for just this. Did you only do it for just this? Or was this simply one of the factors why you moved away?