LLMs are breaking 20 year old system design
1–10 of 31 posts
Re: LLMs are breaking 20 year old system design
#2? Yes if you treat llms like deterministic computation you'll get fucked, news at eleven. In terms of apps "shitty but uncannily useful search" seems like a better fit
Re: LLMs are breaking 20 year old system design
#3Durable is used 13 times in this article.
Re: LLMs are breaking 20 year old system design
#4> LLMs just make this problem more visible.
This theme keeps popping up everywhere. Lots of things were "the way we did things" because a lot of reasons. LLMs just amplify some things and they get enhanced visibility. It can be a good thing, if you're able to understand what/why/how changed, or it can be a bad thing if you insist that "this is how we do things, because this is how we've always done things".
Re: LLMs are breaking 20 year old system design
#5> LLMs just make this problem more visible. This theme keeps popping up everywhere. Lots of things were "the way we did things" because a lot of reasons. LLMs just amplify some things and they get enhanced visibility. It can be a good thing, if you're able to understand what/why/how changed, or it can be a bad thing if you insist that "this is how we do things, because this is how we've always done things".
> or it can be a bad thing if you insist that "this is how we do things, because this is how we've always done things"
Or... maybe... just maybe... it can be a bad thing, because it's a bad thing.
Re: LLMs are breaking 20 year old system design
#6> LLMs just make this problem more visible. This theme keeps popping up everywhere. Lots of things were "the way we did things" because a lot of reasons. LLMs just amplify some things and they get enhanced visibility. It can be a good thing, if you're able to understand what/why/how changed, or it can be a bad thing if you insist that "this is how we do things, because this is how we've always done things".
> or it can be a bad thing if you insist that "this is how we do things, because this is how we've always done things" Or... maybe... just maybe... it can be a bad thing, because it's a bad thing.
Many things can be wrong, for many reasons. The problem is when people think LLMs make it wrong, instead of understanding that LLMs just expose the thing for what it was. It's like shooting the messenger just because the messenger is an LLM. That was my point, in case I worded it badly.
Re: LLMs are breaking 20 year old system design
#7> LLMs just make this problem more visible. This theme keeps popping up everywhere. Lots of things were "the way we did things" because a lot of reasons. LLMs just amplify some things and they get enhanced visibility. It can be a good thing, if you're able to understand what/why/how changed, or it can be a bad thing if you insist that "this is how we do things, because this is how we've always done things".
or maybe it is a bad thing, because right now the model is "throw it against the wall and see what sticks or how many billions we need to make it stick"?
Re: LLMs are breaking 20 year old system design
#8[dead]
Re: LLMs are breaking 20 year old system design
#9> Long running work: an agent doing a 10 minute task isn’t a ‘request’, it’s a long-running async process.
Correct, but we solved this a long time ago when we started sending files to servers to be converted, for example. We either got a 'job_id' or a call to a webhook when the job was finished."
Re: LLMs are breaking 20 year old system design
#10It feels like the virtual actors are the primitive the author is reaching for. As an erstwhile Elixir hobbyist I've often found myself wishing for the simplicity of actors when solving problems in my day job. I tend to work in an AWS environment, but I believe over in Azure they have something like it. I think it was called Orleans when I read about it but I think it's got a more corporate name now.