[flagged]
What it feels like to work with Mythos
211–220 of 337 posts
Re: What it feels like to work with Mythos
#212Earlier 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…
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
Re: What it feels like to work with Mythos
#213Earlier 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 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 “fixes” on top.
I’m not saying that you can’t use AI to do it because I believe that with carefully controlled workflows and context management you can, but it’s not a simple prompt away, it’s requires guidance and understanding, and isn’t the speed demon that raw prompting is.
Re: What it feels like to work with Mythos
#214Earlier quoted context omitted.
I'm happy to discuss arguments if you want to add any?
Not OP, but for me, this model will get VERY expensive in 2 weeks. Now it is part of Pro plan, after 22nd it will get excluded and I will pay by token API usage (~10x more expensive). I find it good for code reviews.
Yeah my time scale is 'a handful of years' :)
Re: What it feels like to work with Mythos
#215Earlier quoted context omitted.
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.
> 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.
Exactly - the normalization of craft (?) is interesting
Re: What it feels like to work with Mythos
#216What 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 / humans if it can do things that you can not achieve. But if it still does errors, how could we ever know that super-invention by AI is not wrong?
If we can not rely on the correctness of the result, it is not usable at all. AI must create reliable and correct results always. That was a very fundamental requirement for computing. This problem has not been solved.
Re: What it feels like to work with Mythos
#217This little line from the article scares me: "but a software engineer would iron out the remaining potential bugs that I could not find quickly" Every sw dev knows this is a very dangerous, and unrealistic, assumption.
it's basically a tiny statement that kind of hand waves all the 'actual stuff'.
It's "I did the first/easy 90% now someone else do the second/hard 90%". Same as it ever was.
Re: What it feels like to work with Mythos
#218Earlier 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…
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 and makes a mess in one? How much work did it saved?
And the elephant in the room is when models actually outperform whatever the prompter is able to deliver, and faster. That is somehow left out.
Re: What it feels like to work with Mythos
#219Earlier quoted context omitted.
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.
> 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.
Re: What it feels like to work with Mythos
#220Earlier quoted context omitted.
My Opus 4.8 regularly works for 10+minutes on a single non-trivial coding request.
Your Opus 4.8? Is it now usual to refer to LLMs like that?
I probably should have used 'Opus 4.8 in my Claude Code configuration'. The model and harnass might be yhe same for everyone, but the .md's, hooks, skills, agents, MCP ... configurations make everyone's setup fairly unique.