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.

I've been at ESUG a few years ago. I can definitely recommend it if you want access to all kinds of Smalltalk and Pharo experts, and listen to all kinds of topics that contain a high amount of expertise.

I remember that I wanted a visual step by step debugger for a visualization library [1]. I was lucky enough to find the library maintainer himself. He liked the idea, and within just 30 to 60 minutes we programmed a prototype in (this was around ChatGPT 3.5, so pure hand coding).

[1] https://github.com/pharo-graphics/Roassal

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?

> I don't even see salary or what your debt is as "personal information" (am Swede not in Sweden), personal information is stuff that no one else would need to know. What people earn affects not just people around you and others in the workplace but also society at large, makes a ton of sense for that stuff to be public.

In a high trust culture I get this. But what about if you're in a low trust culture with quite some "not so orderly behavior" (if you will).

Yea that's a good book. I haven't fully read it but even reading a little of it or checking out the Norman Door on YouTube [1] is awesome.

[1] https://www.youtube.com/watch?v=yY96hTb8WgI

That it says something about the human brain seems to be about right. If you have 8 planets and 8 children it means you've classified certain things you've seen to be part of the same concept and you group them together.

> Clipboard history, but also just "oh you have these windows open while working on this task".

I feel this. When I first got to learn what a workspace was (in Eclipse, of all things), and I really drilled down into the English meaning of it (I'm Dutch), I thought about exactly what you're describing right now.

Yea I get the bearishness from my own personal experience.

Personally, I use LLMs for a lot of things. Oftentimes, I'm a think out loud type of person so even having something that feels like a rubber duck, but more competent, is already amazing for me. And LLMs are a lot more competent than a rubber duck.

But especially sometimes I've noticed that LLMs can be unbelievably stupid. It recently happened a few times with Fable 5.1 as well. Ultimately, I think it comes down to that LLMs can't think broadly. In software development one can usually see this too. For example, a whole app might be built by an LLM and it didn't spend a single token thinking about security because the prompter is at the level of "build a dating app for dogs, make no mistakes". Now you have a dating app for dogs that is insecure.

Since I prompt for almost everything in my life to have an LLM as a sounding board, I'm usually not an expert either. I've noticed LLMs are amazing at "bulk search engine information aggregation" (or whatever you want to call it). So if I need something from the Dutch government, I can find it way more quickly. But oftentimes I've noticed that going for a walk and thinking about a particular thing I'm facing is a more effective way of finding a good solution.

Other times times they are not incredibly stupid, but can't form a strong opinion. This usually happens when I'm tackling a wicked problem [1]. When that's the case, prepare for LLMs to sway with you for every small change in your opinion that you ever will experience.

So I agree: drop in replacement for knowledge workers? No. Rigorous specification is usually needed yes. Though, the small win here is that it doesn't always need to be as rigorous as programming is and it can happen in natural language. It depends on the topic/problem being tackled.

I really like them as UX tools though. Amazing for interactive prototyping and requirements elicitation. And that also corresponds with what the author is saying. Though I find it a bit of a disservice saying "just 3". You know how hard requirements elicitation is? It became a whole lot easier thanks to LLMs (I might change this opinion in a year, haha, but this is the opinion I hold now).

[1] https://en.wikipedia.org/wiki/Wicked_problem

I posted this because recently I'm hitting my stride on Math Academy [1, 2]. So I got a bit curious about the people behind it. Turns out, I'm now questioning: how fast can I learn things really?

Because if kids can go this far. Then how far could I go? How far could we all go?

Also: I'm having a blast, quite literally. Love raving while mathing, it's my new favorite hobby. Shout out to Nigel Good. Nigel sure know's what's good when EDM is considered.

[1] Having 100+ hours of good EDM tracks apparently motivates me a lot. There are papers that mention it's not the best for focus, but I've noticed that I don't do any math at all if I don't feel the warm synths that I love with my favorite playlists [3] (I take a lot of care in constructing them). I'm curious to see if this will keep up since I've only been going hard at it around late August.

[2] https://mathacademy.com/

[3] My main playlist: https://open.spotify.com/playlist/3BUgKCDAWvcDa28MVToIFM?si=...

Thanks for figuring that out. Sort of sounds like AI programming programs to find vulnerabilities, of which fuzzing is one of the proven techniques to do it.

You mean their own trained models, or do you think it's an open source model that they fine-tuned? If they use their own, I'd guess it's the latter.

Wow, this announcement is good content marketing.

Don't get me wrong, it's interesting. But there is no technical discussion as to how they did it. It's simply: we did it and Mythos and Codex didn't.

It's good to know that it's possible, but I'd have already expected it. Put a base model versus a base model + harness + whatever else, and yea, if you do it right then you have a better system to find vulnerabilities.

> We then ran AISLE's autonomous AI system against curl.

They don't even mention what models the use under the hood. It wouldn't surprise me if they are from Anthropic and OpenAI.

Here is a sketch of my argument. It would need tidying but that would require a lot of work.

I've been calling LLMs digital intelligence. That's in my opinion what they are and on the digital/conceptual realm they are better than humans since LLMs are better generalists.

But I'd never state their conscious. For me consciousness extends outward from myself, since I can't trust anything else. It starts with the question like: why can't I control the movement of another person? Why can't I transfer my mind to another body and theirs to mine? Why is it that whenever I sleep, and similar things, I end up back to this place called "reality"?

I come to the conclusion that I am conscious and I'm a conscious being in reality. I am human and I've been raised by humans. Now, technically, all humans besides me could be zombies. They could be non-conscious beings that simply can act like humans. I'm sure we'll be able to create them in a few decades. However, I'm incentivized for multiple reasons to believe they're not zombies. Therefore humans are conscious too. All of them. Can I know for sure? No since I can't even trust my own senses fully or my own thoughts (the whole Descartes thing) but I choose to trust those things too because I need some reasonable-ish foundation to work from.

If humans are conscious, why aren't animals like us? Surely great apes must be conscious at least to some extent. Hell, some of them even have better short-term memory than us [1]. Well, turns out, from an anatomy standpoint they look a lot like us. Fine, let's assume they're conscious too.

Now we get into the territory that anything that has a large enough brain must be conscious because that's how we govern our consciousness. So you can extend this to all kinds of living beings.

I did this from my perspective. Of course, you should do it from your perspective. The same argument could be made.

For as long as we can't manipulate conscious experience in some way shape or form, we have no clue whether anything that isn't like us can be conscious. We'd need to be able to merge and split conscious experiences or we'd need to be very strongly able to understand why that isn't possible. And I don't mean just at the biological level but at the experiential level. Currently conjoined twins, and what they tell us gives some insight (being able to sense the other part that's part of the other twin).

Other than that, I claim we have no clue what consciousness is other than that we're experiencing it. So to call LLMs conscious is way too big of a claim. But they are definitely intelligent because they come up with things that I wouldn't have and it's useful to me. Perhaps a practical characterization of intelligence but it works for me.

I think for anyone to say something useful from this you'd need the trifecta of deep neuroscience knowledge, deep philosophy knowledge and (at least) a strong understanding of how LLMs work.

Hmm it's being done in a less cheesy way than AI does it.

AI text feels more like "this matters, not less." There's always an "it's x not y" pattern somewhere.

It could be written AI assisted but then look at his account. IMO every HN account that was created before ChatGPT came out has incentive to be written by a human since they have a paper trail before the whole LLM thing happened.

This is at least written by a human, not AI, totally human, (digital) pinky promise ;-)

Given the time we live in, I thought it'd be nice to share this old gem and have a discussion started on architecture. It could be about this book or about more contemporary examples. I do like the fact that these are all examples of actual projects.

I once celebrated my birthday where I asked everyone to give the following gift to me: create a presentation or workshop about something you're passionate about in your life. Treat us like experts and go down into your level of thinking, even to the tiniest amount of details. Don't be afraid if we don't fully follow or ask you to explain some terms. I'm hyped to hear what you come up with.

It was such a fun birthday. It was basically a conference, haha.