Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

What it feels like to work with Mythos

oneusefulthing.org

Post reply on HN
Print view View original

161–170 of 337 posts

Re: What it feels like to work with Mythos

#161

Post by matheusmoreira »

selfawareMammal wrote: post #30

What are people working on that they see such a substantial difference between Mythos and Opus? I'd say I'm working with advanced stuff and more than often Deepseek is even more than enough. Why is everybody a genius in here?

I'm working on my own programming language. I've also been exploring open source projects to contribute to. Maybe something that helps me pivot from hobbyist to professional. If such a thing is even possible in this day and age.

Fable 5 found quite a few issues Opus 4.8 missed on code review, even though the stupid cybersecurity nonsense downgraded it. I can't tell you more, I only get a single session per 5h window on Max 5x. Only ran two sessions so far.

Re: What it feels like to work with Mythos

#162

Post by dchftcs »

cgearhart wrote: post #83
eithed wrote: post #38

What I find fascinating that there is so little substance in this article about the quality of produced code and the medium. Is the code documented and tested? Is it understandable and extendable? Is it secure? What language, framework, database was used? Author mentions judgement and taste - well, is the code tasteful? Will the model rearchitecture the entire thing if I ask it to add new functionality, spending anot…

I’m starting to realize that LLMs are really good at building low-stakes projects. Your questions mostly presume that the stakes are higher. The software will last a long time; the requirements will evolve; we can’t tolerate mistakes; etc. The trick to getting good at using LLMs for software is to learn how to make _all_ projects low-stakes.

If there's a viable way to make all projects low-stakes we'd have done it. Consider this: microservices.

Re: What it feels like to work with Mythos

#163

Post by ncruces »

rpdillon wrote: post #136
cgearhart wrote: post #83

Earlier quoted context omitted.

I’m starting to realize that LLMs are really good at building low-stakes projects. Your questions mostly presume that the stakes are higher. The software will last a long time; the requirements will evolve; we can’t tolerate mistakes; etc. The trick to getting good at using LLMs for software is to learn how to make _all_ projects low-stakes.

This is really insightful, but I think it also extends to making the project either low stakes or low complexity. I have this lurking feeling that the preferable architecture for software will change as a result of LLMs because they're good at working on low complexity modular components more than they are on high complexity million-line code bases.

You'll just shift complexity to the orchestration of the modular components.

Monoliths vs micro-services.

Re: What it feels like to work with Mythos

#164

Post by kesor »

coldtea wrote: post #106
eithed wrote: post #38

What I find fascinating that there is so little substance in this article about the quality of produced code and the medium. Is the code documented and tested? Is it understandable and extendable? Is it secure? What language, framework, database was used? Author mentions judgement and taste - well, is the code tasteful? Will the model rearchitecture the entire thing if I ask it to add new functionality, spending anot…

> What I find fascinating that there is so little substance in this article about the quality of produced code and the medium. I clicked one of his examples intrigued "a snake game where the snake is self-aware and crazy things happen;". Played for 1-2 minutes, and it's the classic 1980s snake game. Am I missing something? What is "self-aware" about it? Some funny messages at the bottom of the screen? And what are th…

You didn't play long enough. There are layers and layers and layers of features in that game if you play for 10 minutes or more.

Re: What it feels like to work with Mythos

#165

Post by skydhash »

spicyusername wrote: post #154
eithed wrote: post #38

What I find fascinating that there is so little substance in this article about the quality of produced code and the medium. Is the code documented and tested? Is it understandable and extendable? Is it secure? What language, framework, database was used? Author mentions judgement and taste - well, is the code tasteful? Will the model rearchitecture the entire thing if I ask it to add new functionality, spending anot…

the quality of produced code and the medium A thought I have been tossing around in my head as the models get better is that it really may not matter what the code looks like. If the observed behavior of the software is good, then the software is good. If a bug, of whatever kind, can be fixed by a model on a vibe-coded codebase, then that's a fixable bug. If there are no exploitable vulnerabilities, then the code is…

The thing is that a lot of code rely on multiple layers of abstractions with their own correctness and failure states. And then you overlay the domain correctness and failure cases on top of that.

But all of those correctness are imaginary. The hardware only enforce a few (and it may be buggy). The OS adds some more (and it’s buggy). The compiler/interpreter may have bugs (but that’s rarely a nuisance) and the libraries are often brittle. There are cracks everywhere in the tower of abstractions.

The code has never mattered. What has always mattered is the knowledge of what is the model of correctness of the software (programming as a theory by NauR), so that you can discern where a program is wrong.

The thing is a crash or some other immediate errors are actually nice to have. You get to react immediately and can have a core dump or a stacktrace that points you the error. What is truly a terror is silent corruption (wrong order of operations, wrong values for a comparison that has expanded the idea of correctness, security issues that has been backdoored for years,…).

As Hoare said:

  There are two ways of constructing a software design: One way is to make it so simple that there are obviously no deficiencies and the other way is to make it so complicated that there are no obvious deficiencies.
  The first method is far more difficult.
LLM are very much the second kind. You write a lot of complicated code, and then you can no longer reason about their correctness.

Re: What it feels like to work with Mythos

#166

Post by DrJokepu »

qaq wrote: post #92
cgearhart wrote: post #83

Earlier quoted context omitted.

I’m starting to realize that LLMs are really good at building low-stakes projects. Your questions mostly presume that the stakes are higher. The software will last a long time; the requirements will evolve; we can’t tolerate mistakes; etc. The trick to getting good at using LLMs for software is to learn how to make _all_ projects low-stakes.

You don't need LLM for that. You make _all_ projects low-stakes by working on green field project using (insert buzzword soup of the day) and leaving for a new green field opportunity (that requires experience with buzzword soup of the day) before the project ships.

No, what you’re describing still requires you to do some actual work, and also, while you work there, there is still some level of accountability. A much, much better grift is coaching.

Like, an AI coaching session for executives at the yearly executive retreat. You show up, spend a few hours going through some nonsense slides ChatGPT put together for you, you charge an eye watering fee for it, HR or whoever organizes it will gladly pay for it because it will make them look all cutting edge in front of the CEO, by the next day everyone will forget about it. No accountability at all!

Re: What it feels like to work with Mythos

#167

Post by fwip »

chickensong wrote: post #140
eithed wrote: post #38

What I find fascinating that there is so little substance in this article about the quality of produced code and the medium. Is the code documented and tested? Is it understandable and extendable? Is it secure? What language, framework, database was used? Author mentions judgement and taste - well, is the code tasteful? Will the model rearchitecture the entire thing if I ask it to add new functionality, spending anot…

You probably don't care about the ingredients or engineering of asphalt, only if the road does its job well or is filled with potholes. Outside of the software industry, nobody gives a shit about code or databases.

Sure, but if there's a trillion dollar company saying that it's going to replace all our road workers or engineers - I'd want to listen to the opinion of an expert. Some reporter from CNN driving over it like "yeah seems good to me, good this" has approximately zero persuasive power to me.

Re: What it feels like to work with Mythos

#168

Post by fwip »

adamtaylor_13 wrote: post #63
eithed wrote: post #38

What I find fascinating that there is so little substance in this article about the quality of produced code and the medium. Is the code documented and tested? Is it understandable and extendable? Is it secure? What language, framework, database was used? Author mentions judgement and taste - well, is the code tasteful? Will the model rearchitecture the entire thing if I ask it to add new functionality, spending anot…

I'm becoming more convinced these are questions of the Before Times. Yes, yes—heresy, I know. Yet, I can't deny the reality that I observe working with LLMs every day. If this truly is a step-function (as some are sgguesting), then I have absolutely zero concern for the quality of the code.

Kind of a circular argument, isn't it? "Some people are saying it's very good at coding. If that's true, I don't care if the code is good."

Re: What it feels like to work with Mythos

#169

Post by rspeele »

warkdarrior wrote: post #95
Ferret7446 wrote: post #76

Earlier quoted context omitted.

Humans are very expensive, so the equation almost always falls against them. It's not just salary, but also safety/labor regulation, legal risk, vacations, sick time, personal conflicts, HR, benefits. Even when automation is more expensive on paper, it's generally still cheaper

That's the beauty of these AI advancements. You, a human, will have to compete against a model for the same job. If you get $100,000 per year as a SWE, and Anthropic offers a coding model for $100,000 per year (but working 24/7), then you'll have to give up all of those addons that make the fully burdened cost of the employee. Say goodbye to vacation, sick time, benefits, etc.

> "What have you got against machines?" said Buck.

> "They're slaves."

> "Well, what the heck," said Buck. "I mean, they aren't people. They don't suffer. They don't mind working."

> "No. But they compete with people."

> "That's a pretty good thing, isn't it--considering what a sloppy job most people do of anything?"

> "Anybody that competes with slaves becomes a slave," said Harrison thickly, and he left.

Kurt Vonnegut, Player Piano

Re: What it feels like to work with Mythos

#170

Post by crystal_revenge »

jimbokun wrote: post #116
eithed wrote: post #38

What I find fascinating that there is so little substance in this article about the quality of produced code and the medium. Is the code documented and tested? Is it understandable and extendable? Is it secure? What language, framework, database was used? Author mentions judgement and taste - well, is the code tasteful? Will the model rearchitecture the entire thing if I ask it to add new functionality, spending anot…

Does it matter to the people requesting the software if it acts in the way they expect?

We've lived in a software bubble for so long, most software engineers have completely forgotten that the purpose of (most) software is to solve a problem. If that problem solves the problem well and reliably it doesn't matter the quality of the code.

In fact, that's the entire reason we care about "quality code", because we assume that quality code is code that does what you expect well and consistently.

I say this as someone who hand writes code pretty much every night for fun, just to experiment with computation. Which, oddly, is more fun than ever because I don't feel like there's any need to connect this type of programming with "real world software", and I can really enjoy code for it's own sake, meanwhile my job is mostly just running agent loops (which I quite like as well).

Post reply on HN