Okay, I think that's fair, but I'm not convinced there's anybody actually doing large amounts of compute on office tasks? Do you know anybody? Can you point to anybody publicly documenting this? Can you can you point to any specific workflows where fable is being used in lieu of more basic models?
Even if you provide exceptional answers for all of these I still think it is disingenuous at best to ignore coding tasks in writing this. I have to assume coding is 90% of the use cases for the frontier.
You've made a case that the labs need these customers. You haven't made a case that the labs have these customers.
I was actually shocked to see that much improvement on GLM 5.2. I am getting pretty great rates in GLM5.2 right now and I'm extremely happy with the output. I have found Kimi to be generally a little slower but noticeably better at architecture and structuring things. I would have thought is for sure currently more expensive than GLM5.2, particularly with subscriptions etc, but I'm excited for this to decrease further.
I'll also say - scum gave a presentation which was actually very touching. "Love what you do, care deeply about your projects, be with your family". Combined with everything you already said - pretty awesome stuff
Yeah, I mean I guess I could technically connect to the remote SQLite server on my production server. You're right. But I've never done that and that's just not the pattern people use on SQLite
I personally find Postgres WAY easier than SQLite simply because of the deployment story. I do a lot of hotfixes and dangerous stuff on personal projects, and having two databases complicates that tremendously. I like being able to run hot code on prod.
For the record, this is not the same reason I like postgres for actual production code
This makes total sense, thank you. I come from a Python background and appreciate a similar philosophy in Ruby, which is that sometimes it's just nicer and easier to not do typing. It's okay to prioritize aesthetics and ease in code.
I've gone much deeper into type checking since then, but I still like simple, dynamic scripting.
I've heard "functional core, imperative edges" and I feel like that kind of applies to static vs dynamic. I think there's a lot of cases where exposing a scripting language is a perfectly sane and good design pattern.
I'm not sure Emacs fits that category, hah, but it's just so dang useful.
I had not heard of control theory, I appreciate this
Thank you for checking it out! Fair warning, it's vibeslop and I really don't have a clue what I'm doing. I have very little background in compilers or FP or really anything. I'm honestly just shocked at how well it works.
If you want to kick the tires on it or even if you just find it interesting, please feel free to reach out! I'm kind of obsessed with this thing now, and would love and appreciate any feedback
This is a good discussion of these principles. Largely inspired by Emacs, I built an interpreted lisp which runs in a web server and stores the AST Postgres. It gives me this kind of malleable computing and a Lispy feel with very little overhead.
Instead of calling an API, agents can just use functions in a REPL. They can also write new views and improve the program if they run into an issue. Honestly, pretty amazing stuff.
Being able to design a program specifically for the workflow I want is pretty neat. There's some vibeslop jank, but Emacs is a little bit jank too.
I had the same thought - but maybe it's good? I was thinking that if you have a decentralized store than you can connect to it regardless of dev environment. I've used XMPP for orchestration but I can see ergonomic advantages to this.