jdmoreira

then they copied that from codex because thats exactly how codex works

Great video by the way. Extremely good!

I don't want to sequence at home.

But I do want to sequence it using a third-party that gives me all the raw data. I live in Europe and I'm just a simple consumer. Does anyone know how I can do this? What service would I use / you can recommend?

Them not keeping it on their side would be a huge bonus of course but not sure I can ask for that much.

Just out of curiosity, what is your legitimate criticism of Adreessen and Sacks?

I would add, simple data in / data out functions. Composable functions. Value types > reference types. Keep your state in order! Consolidate your state, dont shatter your state around a bunch of "objects"

Uncle Bob is a snake oil salesman. Not sure he realizes it himself though. The whole SOLID, OOP design patterns era was one of the worst things to have happened to programming.

I always thought I was the one that sucked but now I'm absolutely certain that whole zeitgeist was total crap.

What? On a micro immediate mode UI?

Really insane comment TBH

How so? Happy to test a solution!

I have a version of this where I have the llms play the duel decks "Elves vs Goblin" against each other using xMage as a rules engine.

Unfortunetly it gets really expensive to run even with some optimizations for the context.

I can only afford to play them with the deepseek models. They make serious blunts sometimes. This is not an easy "harness" to build and I dont have the time or disposal cash to work on it. I think a lot of work could be done on improving it still and testing better models.

It would make an amazing "arena" bench. There is plenty of more duel decks well balanced against each other.

> I feel like I'm missing a mode that works more like a pair programmer. Perhaps a multimodal model that can talk to you about what you're writing, as you write it, and offer suggestions rather than trying to take over and do everything for you.

This is exactly what I have also been thinking and wanting for a while now. A realtime agent that I can share a screen and mouse / keyboard with. and we can just work together at times. I think it will probably come at some point but we might be a few years away from it.

No I wasn't.

This is the whole paragraph:

> People used to have nothing. My grandfather got his first pair of shoes when he was 10 years old. Yet he was more joyful and positive than most people alive today.

I was saying he had nothing, not even shoes (and people now have plenty).

This shouldn't be hard. It's truly basic text comprehension.

did I compare AI to shoes anywhere in my text? They also used to teach comprehension when I went to school.

It’s sad that we ended up here. I can’t fathom that young people aren’t excited about technology anymore.

I was young once and naive, and I read a bunch of sci-fi. I could never have imagined having these LLMs or coding agents during my lifetime. Never. It was unthinkable to me that something like this could even happen.

And yet, here we are.

Even if you think it’s just a statistical trick, you should still be blown away.

You should also be optimistic, because that’s what we need young people for. We used to be able to convince young people to get on boats and migrate halfway around the world to die on some godforsaken land. Or get on boats and go fight some ideological war somewhere else (not saying that was a good thing). But now we can’t even get them excited about technology?

What have we done?

People used to have nothing. My grandfather got his first pair of shoes when he was 10 years old. Yet he was more joyful and positive than most people alive today.

I really really like mise! I've been using it for everything lately. all my repos / projects now start with a mise.toml

Wow. I spent a lot of time, probably around the year 2000, playing UO on a Portuguese shard named "Lusitania".

Such great memories!

I didn't say we should assume LLMs are intelligent. In fact I always thought they weren't because they only "forward pass".

But then they came up with the whole "Reasoning model" paradigm and that contains obvious feedback loops. So now just throw my hands in the air because I think no one really knows or can tell for sure. We are all clueless here.

I can really recommend this book by Douglas Hofstadter: https://en.wikipedia.org/wiki/I_Am_a_Strange_Loop

You can only be certain you perceive it and you can't be certain others perceive it (or if others exist at all of course).

The only thing you can really tell is "I perceive myself in some sort of feedback loop manner". Which to me it even sounds like it has "arisen" from underlying mechanisms.

It's starting to look more and more to me as if conscious is just an illusion that we ourselves perceive. There is nothing fundamental about it, just an artefact of a certain style of computing as perceived by the reasoner itself.

We look at the current llms and because we see them for how they are fundamentally operating we assume they can't be "conscious" but we really don't even know what conscious is. The only people in the world that know ANYTHING about conscious are anaesthesiologist - they know how to turn it off and on again. What does that even tell you about conscious?

> If I had $200 Billion I would literally give all of it to be a teen again for ten years from 1990 to 2000 again.

I so so wish I could go back as well. Its such a magical time in my memories. I was 6 in 1990 and I was 16 in 2000. God, what a world that was!

I recommend you search "Premodern MTG" and "Oldschool 93/94 MTG" ;)

This is the complete opposite of Hofstadter's "Strange Loop" hypothesis, which intuitively makes much more sense to me.

Humm... better than Opus 4.6 or 5.4?

What are you using for the frontend? React component libraries?

Just use DaisyUI

are you seriously comparing AI to tulips? I don't even know what to say. Even if you are very bearish about the technology certainly you can't be this detached from base reality. Yet here we are

Talent is evenly distributed, opportunity is not

As a senior engineer if your value add was "accumulated expert knowledge". Then yes, you are in a bad place.

If instead it was building and delivering products / business value. Good judgement, coordination and communication skills, intuition, etc… then you are now way way more leveraged than you ever were and it has never been greater.

Not sure I understand your point. Under WebAuthn / FIDO2 you can't impersonate a RP

Could you explain better?

can be solved with a hybrid model that degrades when the central service is down. No?

Sure... but it should degrade to work when the central services are down.

You should still be able to authenticate with each individual service when the centralised service is down.

There is no reason why you shouldn't be able to login to your bank under these circumstances.

These things should be offline / resilient first right?

Smartcards / YubiKeys.

Never understood the logic for these to be centralised / online.