Nice, but I'm really curious about how many tokens have been used.
There is only one hint: 475k tokens in the screenshot when OP asked the model to fix some behaviour, but it would be fascinating to know the total tokens amount.
What it feels like to work with Mythos
81–90 of 337 posts
Re: What it feels like to work with Mythos
#82Man, 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.
I wonder what Vogons would think of it.
Re: What it feels like to work with Mythos
#83What 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.
Re: What it feels like to work with Mythos
#84Earlier quoted context omitted.
Less fascinating when you consider that this is a non-coders perspective.
Fair enough, but enterpreunership should, I guess, ask questions if given Next Big Thing has substance behind it or is it just snake oil.
Ah, but billions of dollars depend on those questions not being asked in a genuine manner. Don't you want a slice of that or are you an... AI skeptic thunder clashes.
Re: What it feels like to work with Mythos
#85I have been using it for less than an hour so take this with a grain of salt of being excited for the new tech. In a project like mine ( https://github.com/tsz-org/tsz ) I am constantly frustrated that models were not doing enough research and were not taking into account other situations. Again and again models would produce code that would fix one thing and break 2 other tests that were "unrelated". With Fable it s…
Does this not indicate that the project might not be structured in an appropriate way that allows incrementally adding features?
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
Re: What it feels like to work with Mythos
#86Earlier quoted context omitted.
In my mental model, "my Outlook" is the outlook instance running on my computer, on my data. My outlook crashed today. Yours might not have crashed. Similarly, my Jira contains tickets about my work, your Jira does not contain those same tickets. That might be technically the same instance on the same SaaS server, but the server I'm routed to accessing my data with my credentials turns it into "my Jira". My Jira is s…
This is completely fine, as those are your own installs, but LLMs can't be owned by the users, your Opus is the same Opus as everyone else's, your only difference is the suscription tier to their API. If you had your own on-premises LLM, that would indeed be your LLM, and it would make sense to compare it to the on-premises LLMs of other people, as your setup particulars would affect the result.
The copyright to the Outlook binary isn't owned by the users either, even if they're running it on local hardware. The Opus 4.8 weights are (we assume) the same between users, but the conversation/tooling state is not shared between them by default. I prefer to route around this construction myself, since I do think there's some ontological slippery-slope potential, but from a lexical perspective I think “my” is a perfectly defensible abbreviation in context.
Re: What it feels like to work with Mythos
#87>Ethan Mollick Just an FYI this guy is an AI hype-beast. Some of his tweets are truly out there.
Huge fanboy for sure
Re: What it feels like to work with Mythos
#88What 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.
> The trick to getting good at using LLMs for software is to learn how to make _all_ projects low-stakes.
this doesn't really work in the real world. There are many things that actually matter, engineering is fundamentally about handling them.
Re: What it feels like to work with Mythos
#89My wife likes to say "feelings aren't facts"
Re: What it feels like to work with Mythos
#90I have been using it for less than an hour so take this with a grain of salt of being excited for the new tech. In a project like mine ( https://github.com/tsz-org/tsz ) I am constantly frustrated that models were not doing enough research and were not taking into account other situations. Again and again models would produce code that would fix one thing and break 2 other tests that were "unrelated". With Fable it s…
Does this not indicate that the project might not be structured in an appropriate way that allows incrementally adding features?
In general, sooner or later you need to restructure one thing or another when requirements are changing. Good code lets you reason about a refactoring, and experience tells you when it is necessary or appropriate. Coding agents aren’t very good at the latter.