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

221–230 of 337 posts

Re: What it feels like to work with Mythos

#221

Post by vrganj »

locknitpicker wrote: post #208
phil21 wrote: post #183

Earlier quoted context omitted.

> I think the entire definition of technical debt has changed. I’ve been sceptical of these tools and still approach their output with caution. This very well summarizes my current thinking on the subject as well. And most of my career has been playing the role of technical debt nazi. Much to the detriment of my earning potential. Does AI make incredibly inefficient code most of the time? Yup. But it does it at light…

> Does AI make incredibly inefficient code most of the time? Yup. But it does it at lightspeed with minimal effort. This hits the nail in the head. Detractors often hang on to examples of coding assistants making mistakes or output subpar code, but they somehow miss the fact that coding assistants can also be prompted again and refactor whole swaths of code just as fast as they introduce oopsies. This means that the…

In my experience, the refactors are just as bad, just in different ways. All you end up doing is treading water with different iterations of shitty code. By the time you get somewhere acceptable, you could've just fixed it up yourself.

My preferred workflow these days is to pair program with an LLM until it gets close-ish and then manually touch it up. Without that, it just produces junk in different forms.

Re: What it feels like to work with Mythos

#222

Post by asoderlind »

locknitpicker wrote: post #208
phil21 wrote: post #183

Earlier quoted context omitted.

> I think the entire definition of technical debt has changed. I’ve been sceptical of these tools and still approach their output with caution. This very well summarizes my current thinking on the subject as well. And most of my career has been playing the role of technical debt nazi. Much to the detriment of my earning potential. Does AI make incredibly inefficient code most of the time? Yup. But it does it at light…

> Does AI make incredibly inefficient code most of the time? Yup. But it does it at lightspeed with minimal effort. This hits the nail in the head. Detractors often hang on to examples of coding assistants making mistakes or output subpar code, but they somehow miss the fact that coding assistants can also be prompted again and refactor whole swaths of code just as fast as they introduce oopsies. This means that the…

I think this is overlooking the fact that assigning a coding assistant to fix the bugs it re-introduces for all eternity just leads to spiraling token costs, which might cost more than just hiring a competent engineer in the first place.

Re: What it feels like to work with Mythos

#223

Post by mohsen1 »

anematode wrote: post #131
mohsen1 wrote: post #85

Earlier quoted context omitted.

the setup is solid. there are thousands of tests and CI won't let things to merge if tests are failing. But overall, this is pretty normal for compilers to have this sort of "unexpected" tests failing due to some work in an area. It happened to me when I was coding everything manually back in the day too

> there are thousands of tests and CI won't let things to merge if tests are failing. That's not what a clean setup means... I mean good separation of concerns, established invariants, etc.

A compiler and type checker is very special case where you can fix something in the lexer or parser and break another thing in AST walker etc. tsz is well architected but those things can happen if you're not careful and that's precisely what I meant in my original comment. Fable can think how changing parser can impact checker etc...

Re: What it feels like to work with Mythos

#224

Post by dkersten »

locknitpicker wrote: post #218
dkersten wrote: post #213

Earlier quoted context omitted.

I haven’t used Fable/Mythos yet, but my experience with recent version of Opus, GPT 5.5 and recent Chinese models is that promoting again isn’t guaranteed to fix the underlying issues, nor is it guaranteed to not introduce more issues. I’ve seen SOTA models make ridiculously stupid architectural decisions that they were then unable to back out of without being prompted very specifically, instead adding a patchwork of…

> I haven’t used Fable/Mythos yet, but my experience with recent version of Opus, GPT 5.5 and recent Chinese models is that promoting again isn’t guaranteed to fix the underlying issues, nor is it guaranteed to not introduce more issues. That's not really the point though. That presumes models are only useful if they are one-shot models. That is false. I mean, what if your prompt successfully changes 20 source files…

> That presumes models are only useful if they are one-shot models

That’s not at all what I’m saying.

I’m saying that in my experience across multiple models, the follow up prompts don’t fix prior underlying issues. They usually patch on top instead, unless you give them significant and time consuming guidance.

I want them to be more useful outside of one-shot uses, but I find that they currently miss the mark.

Re: What it feels like to work with Mythos

#225

Post by michaelteter »

As a software engineer and solution provider, I do not feel threatened by this.

I do not fear that management will get tools like Mythos and then not need people like me. Most of the value I provide is in translating what the management/client _thinks_ they need into what is the real problem and solution.

That's not an insult to them, it's just pointing out that they see only their problem, and they imagine what would be the solution. They then ask for that solution. Quite often, what they want built isn't what they need. And I've seen so many problems, from so many domains and scenarios, that I can usually recognize the core need and propose (and build or direct building of) a solution which resolves that need AND has an eye toward the likely future needs.

Mythos may do an excellent job providing a high quality result based on what is asked of it. But the result will only be as good as the quality, clarity, and presentation of the request.

If I hire a home builder to build me a custom home, that builder is going to ask me a thousand questions - questions I had never even thought of. Mythos isn't going to ask all those questions - it's going to make the best choices it can without the consultant's level of interaction. And the buyer will get what they get. Sure, the buyer can then say, "oh, I don't want any hallways - just connected spaces." Then the house gets demolished and rebuilt to the new, clearer spec. Repeat, repeat repeat. Maybe eventually the buyer gets what they really want. More likely they give up before reaching that point, and they go and hire a real builder.

I'll sum it up like this: You can get great results with minimal effort if you don't really care too much about the details. But if you don't care much about the details, then your need probably wasn't very significant.

Re: What it feels like to work with Mythos

#226

Post by geraneum »

chickensong wrote: post #219
geraneum wrote: post #204

Earlier quoted context omitted.

> You probably don't care about the ingredients or engineering of asphalt Everyone does. You don’t think about it everyday because we’ve delegated it to experts which don’t come up with a new composition of Asphalt every time you press “generate”. It’s rigorously battle tested and short of intentional negligence, it’s consistent. I’m amazed how people are forgetting how the world actually works.

You've missed the point.

The point doesn’t seem to have been thought through.

Re: What it feels like to work with Mythos

#227

Post by alt227 »

rgmerk wrote: post #184
theturtletalks wrote: post #29

This is what he built: https://isochronic-passage-chart.netlify.app/ Doesn’t work too well on mobile but looks interesting

It put the chart title directly on top of Australia. Which just about sums up my experience with using LLMs to code, really (though not with these state-of-the-art models, admittedly) - it's amazing what they can do, but left to their own devices they'll make boneheaded decisions.

I believe thats why they put 'Sydney' as an option at the top to recenter the map.

The real issue with the title is that it doesnt fit in the box!

Re: What it feels like to work with Mythos

#228

Post by nearbuy »

rstuart4133 wrote: post #146
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

> Humans are very expensive, so the equation almost always falls against them. You underestimate what these models cost. Uber's budget is $1,500/dev/month. I gather that was put in place because the dev's were going through $6,000/dev/month, which Uber decided could not be cost justified. Fable costs at least twice as much, or $12,000/dev/month. Fable can apparently work for hours without supervision, which means a s…

These numbers don't mean anything without a denominator. You could burn $10 million/month of tokens if you want. We want to know how the cost per unit of useful output compares to a human. Does $6000 of usage buy you a man-month of work? Less? More?

Re: What it feels like to work with Mythos

#229

Post by zelphirkalt »

michaelteter wrote: post #225

As a software engineer and solution provider, I do not feel threatened by this. I do not fear that management will get tools like Mythos and then not need people like me. Most of the value I provide is in translating what the management/client _thinks_ they need into what is the real problem and solution. That's not an insult to them, it's just pointing out that they see only their problem, and they imagine what woul…

I currently see the problem as follows: The knowledge worker like you sees the need for people like themselves to still be hired, and can reasonably argue for it. However, the management dudes and investors do not understand it, and it is difficult to make them understand, when their (short to medium term) profits depend on not understanding it. So whether you feel threatened or not, is just a matter of you feeling bad or not, but doesn't really matter, when it comes to finding a job.

Re: What it feels like to work with Mythos

#230

Post by zelphirkalt »

Our_Benefactors wrote: post #91
Qhemlomo wrote: post #77

Earlier quoted context omitted.

I'm happy to discuss arguments if you want to add any?

The only thing they’ve overtaken is arguably batteries, and even that is questionable if the quality is as good as Korean manufacturers. I think it’s more likely that the Chinese chip industry overtaking competitors will remain like nuclear fusion, forever “just 5 years away”

They mostly have overtaken in cars too. Their EVs are just cheaper, and they have built the infrastructure around it, even in more rural provinces. Building infrastructure is something they excel at anyway.
Post reply on HN