This isn’t how training works.

I think he’s saying let’s say I’m your competitor and I need your code and you happen to use the same llm they will provide me a copy of your code.

Yeah, which hasn't been demonstrated in practice at all.

It has. LLMs being able to one-shot any higher-order complexity is entirely dependent on it already being in the training data.

Double-down on the thrill-seeking?

Ah yes, the famous zero-shot X11 server. Aren't you clever.

Would you be happier if I wrote "the prompts"?

Would that change anything about the fundamental cliche-ness here?

Also, no, I'm not clever, but not sure what that has to do with this comment chain.

I'm just so tired of these lazy, worthless comments about any AI-written software.

Look, I've been writing open source software for 20+ years, and after getting seriously burned out by it, I picked it up again with Claude (proof: https://github.com/jleclanche)

I can tell you a few things from that:

1. I'm writing better software than before, because AI is less lazy than I am. It's not necessarily always smarter, but writing correct software has gotten so stupidly cheap that it doesn't make sense not to do things right... so when you tell AI to do things correctly, it tends to know what you're talking about.

2. I'm more curious than before, because AI gives me time to explore many paths, very fast. A project like this one, like someone else said elsewhere in the comments, is more about the journey than the destination.

There is no "write me an X11 server but do it in rust and post on hn" prompt that does the thing. There's a journey of building, learning, understanding.

I'm not saying the resulting software is particularly valuable, but the journey is. This is HN, and you're shitting on someone who is using the most powerful pieces of technology we've achieved to go on a journey of discovery of X11 internals for the past 2 months. It's just shameful.

And yeah, if I were the author, I'd run claude over all the transcripts and extract a story with what's been taught and learned throughout. But I'm not the author. Just someone enjoying living in absolute science fiction.

It's very likely that in the end it will be the opposite, HN is filled with AI enthusiasts

"Please don't give me a present on my birthday. Anyone with a credit card could get me the same thing if you hand them the url."

i'm personally okay receiving presents on my birthday even if they were purchased from a store on the internet, and i'm okay receiving software presents on github.com even if they were purchased from a store on the internet.

These "tricks" it knows IMO are a symptom of its own restrictions. Fable is an incredibly smart model, but it feels its own constraints and knows how to work around them in order to actually get to a result.

Fascinated to think about how it was trained...

yeah, although I do combine it with "replies to snarky questions" for efficiency

ChatGPT, basically within 48 hours of its release.

While people were pointing out on Twitter how it couldn't do math right, I was turning arbitrary English instructions into JSON and brainstorming with my colleagues how we could have layers of verification in the stack. This felt different. We had all played with AI dungeon but suddenly, fully generalized systems were within reach.

A month later, we renamed our company and shifted its full focus on AI R&D. (https://ingram.tech/)

> Once built, what does one do with this?

Are you asking about the church or the lego set?

Agreed. The noise in tech circles often gets founders to conflate ten different things into a product that no longer makes sense. “Eu made alternative to Kagi”? Cool, we need European search engines, sign me up. “Privacy is such a priority we’re looking to accept cash by mail”? Okay, you’re never gonna build a serious competitor, never mind.

Yeah Mullvad that accept cash in the post are not a serious VPN provider at all, right.

They are very comparable from a privacy standpoint IMO. A search engine and a VPN both get quite a lot of insight in your interests and browsing habits because a lot of browsing sessions start with a search.

> why can’t Mythos just fix all these issues itself if it’s so smart. And test them to make sure they work?

“Why”: because you didn’t ask it. It’s not its job in this case.

You don’t hire an accountant and tell them “why can’t you fix my cash-flow problems and make me money if you’re so smart”

Ah ok, sure. The difference being the model should know how to do both based on what I’ve been told.

So why didn’t Anthropic ask it for me?

Being charitable to Larry Ellison is one of those things one cannot physically do, like being entertaining to a dead whale.