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

251–260 of 337 posts

Re: What it feels like to work with Mythos

#251

Post by swiftcoder »

ramesh31 wrote: post #176
rstuart4133 wrote: post #146

Earlier quoted context omitted.

> 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…

> I would not be at all surprised if they can put a nought or two on that number. People keep saying this and it keeps not happening. ChatGPT Pro was $200/mo when it launched in '23 for a ~100B class model with 8k context. Claude Max is now the same price for practically unlimited access to a ~1T class model with 1M context. Moore's Law never died, it just switched architectures.

Not to mention, the cost/performance of the baseline keeps falling. The cost-effective Deepseek V4 Flash is better than frontier models from a year ago, at a fraction of the cost.

Re: What it feels like to work with Mythos

#252

Post by Schmerika »

shimman wrote: post #134
jimbokun wrote: post #118

Earlier quoted context omitted.

Well that’s kind of the point. They can just summon bespoke software out of the ether that only handles the use cases of themselves and a few of their collaborators. Making “side projects” was mot possible for non-developers before powerful LLMs. Now it is.

Making side projects isn't a trillion dollar industry tho, adding to the fact that we are facing another global supply chain crisis due to the Iran War; the US is about to commit the biggest self-own ever in the history of empire.

There are actually quite a few trillion dollar industries that exist thanks to "side projects".

Apple was Woz's side project, once upon a time. Adsense came from Google's 20% time. Social media started as a side project.

Forests grow from trees. Trees grow from seeds. More potential seeds = more potential forests.

Re: What it feels like to work with Mythos

#253

Post by redhale »

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 will never stop being fascinated with takes like this. Maybe you're right. But people said very similar things over the last few years and many of those statements look unbelievably naive in retrospect.

Sure, AI can auto-complete the line, but it can't write full functions.

Sure, AI can write functions, but it can't complete full features.

Sure, AI can write full features, but it can't build full applications.

Sure, AI can write full applications, but it can't build them in the right way / ask the right questions / write beautiful maintainable code / do what _I_ do..

Time will tell.

Re: What it feels like to work with Mythos

#254

Post by mieubrisse »

Having a good prompt-engineering skill is the highest-leverage thing IMO, so I burnt 2 Max 20x usage windows to help Fable help me refactor mine. With its partnership we:

- Went deep on "what types of guidance even are there? what does giving good guidance mean?"

- Sampled my existing Claude guidance (CLAUDE.md, skills, hooks, etc.) and broke their guidance into "atoms"

- Categorized them by clustering, the same way Big Five was generated

- Generated a new candidate

- Then used independent agents to compare it against my existing corpus assuming that the new one would be worse

Working with it felt like working with a supersmart entity capable of generating very plausible-sounding but not-necessarily-true statements. The outcome certainly felt like an alien artifact, like nothing I'd make myself.

Only time'll tell if it holds up, but it sure had some interesting ideas.

Re: What it feels like to work with Mythos

#255

Post by varjag »

prmoustache wrote: post #194
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…

> I think many software engineers forget they exist to get real things done (in many cases at least) and they are a cost center for most businesses. If your end product is not selling software, very few people actually Doing the Thing(tm) will give a single solitary care about code quality or maintainability when they can just spend 30 minutes and $15 worth of tokens to fix it. I am suprised to hear people so naive t…

The GP explicitly mentioned "end product is not selling software". But even then, bugfixes introducing new bugs are not unheard of before. Most code used to be mediocre quality so there's not a sea of change with AI. Perhaps it even becomes better on average.

Another thing though is selling software in the first place will soon become tough proposition outside of a few niches.

Re: What it feels like to work with Mythos

#256

Post by throw310822 »

neaden wrote: post #61

Man, that poem it made is terrible. Like just incredibly bad. Sure it's neat that software can make an incredibly bad poem but there is enough bad poetry in the world that we don't need it.

Terrible? Incredibly bad? Something tells me you are not very familiar with poetry, literature or writing in general. This exercise gets its inspiration and tone from one of Stanislaw Lem's Cyberiad short stories ("Trurl's electronic bard"). Besides, what did you expect from a "10 pages epic rhyming poem about a haircut where every word starts with the letter S"? Robert Frost?

Re: What it feels like to work with Mythos

#257

Post by brazzy »

eithed wrote: post #212
locknitpicker wrote: post #208

Earlier quoted context omitted.

> 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…

Don't forget that you can adjust your requirements (either via plan or skill) to ensure the mistakes do not happen. The problem is that neither LLMs, nor humans (that don't work with the domain) will know they made these mistakes. Even coders don't think about everything all the time

> Don't forget that you can adjust your requirements (either via plan or skill) to ensure the mistakes do not happen.

No, you can't. Adjusting prompts ensures absolutely nothing.

Re: What it feels like to work with Mythos

#258

Post by skywhopper »

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.

But not all projects can be low stakes. None of the important ones are.

Re: What it feels like to work with Mythos

#259

Post by fisf »

sexylinux wrote: post #216
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…

It still does make errors, yes? Because it is not usable, if we need to verify everything. AI is only interesting if it can do things that humans can not do. If you can verify results because you can do it yourself, then why use AI? It will just bind highly skilled people to do verification work. Instead these people should do the actual work, results will come quicker. So AI is only interesting to you / your org / h…

By that measure, most software developers should be unemployed.

Re: What it feels like to work with Mythos

#260

Post by jgilias »

Cool. But.

Most of the “impressive” stuff is not “the model” but “the harness”. Spinning up the subagents and teams of lower models, letting them explore, do adversarial coding. It’s all in the harness. Granted, Mythos might be better at that orchestration, but it’s still the harness.

Second is the prompting. The author is an expert in what they’re doing and prompts the system in a way that yields useful results. I see too many people believing that if an expert can achieve those results in a domain they’re familiar with, then them as non-experts will be able to as well. And that’s a fallacy that Mythos doesn’t change.

Post reply on HN