For me, one of the big improvements is the ability to legitimately work via text message. That probably sounds dystopian in a bunch of ways to some people. But there are times that I want to work, but couldn't, previously.
Now I can work from wherever, whenever, by speaking into my headphones, and have it persist. Sure, I want to be in front of a screen to do final syntax review, but I don't mind planning out architecture and guiding an LLM towards a cohesive result while going for a walk or jog. That's just not a workflow that would have been viable 3 years ago.
I always thought of myself as merely ADD, but your comment is so incredibly relatable across all dimensions that I find myself wondering how far along the autism spectrum I am. Although, in my personal opinion, neither term is especially helpful: it's not a sensory/executive processing disorder if it's clearly benefiting both yourself and the people around you. It might make being sociable difficult, but that's the tradeoff for being willing to engage your mind in ways that others filter out as "too much information."
I’d be really careful with language like. For me the sensory and executive components are clearly disordered and border line disabling all on their own., and while it is what “me” is, it certainly isn’t making me or anyone around me happier, or their lives easier. Like - I carry a shoulder bag with industrial earmuffs and extremely dark sunglasses at all times because I cannot function in sensory overload. It is not a super power, and framing it that way is dismissive of those of us not on the very mildest end me of the spectrum.
I apologize. I didn't mean to suggest it is a super power, and it has also been a struggle in my life. I find it useful to frame this way because the struggle is not only because of the way that I am, but also because of the way everyone else is. I'm not asking anyone to change on my behalf, but it took me a long time to accept myself as I am. It took me a long time to accept that I didn't need to change for the benefit of everyone else.
They are building them because they can ask an AI to spin it up. They could have asked it to spin up the public API just as easily. The MCP choice is a fashion choice vs an openapi spec with similar documentation (or any number of other human+machine readable tooling). It might accidentally win or accidentally lose just because of the timing / network effects.
Right; isn't this already captured by an openapi spec with RBACs? Plus the benefit that your ai agent can keep using all the pre-AI tools that already interface with those specs. What is MCP bringing that an openapi spec doesn't?
You can build an MCP client really really easy today with libraries and it integrates with inference calls very well. If you want to give a cloud agent access to another api, you need to bills a connector or give it shell access or some sort of sandbox with tools to access that stuff. That’s fine, but how do you then give it auth access? How do you ensure security boundaries? MCP builds those in and the shape (prompts, resources, tools, etc) are good for agentic work.
It’s like asking why we needed browsers when we had BBSes; they serve a different but similar purpose and are build on different abstraction levels.
Caveat emptor, I'm not a Haskeller, just an admirer. But Haskell let's you run functions over the type system itself very elegantly, so you can have a type that is derived from a type that composes three types that are derived from several functions' declared runtime behavior. This kind of type inference can provide arbitrarily rich information about anything in the entire program, letting you encode more than just range-types etc at compile time.
This comes with some design drawbacks. I think Rust's borrow checker would be implementable but unreasonable in Haskell: Haskell already does lazy-evaluation on types to enable its arbitrary depth of type expressivity. But the borrow checker also wouldn't really make sense for Haskell because the default programming model uses a GC. I think Linear Haskell might be a kind of Rust-in-Haskell, though.
Depends. Within the US, there are data export laws that could make the "whoever" part illegal. There are also conspiracy to commit a crime laws that could imply liability. There are also laws that could make performing/demonstrating certain exploits illegal, even if divulging it isn't. That could result in some legal gray area. IANAL but have worked in this domain. Obviously different jurisdictions may handle such issues differently from one another.
What do you recommend if I've been regularly producing blog-length posts in Slack for years, no LLM present? It's where I write man...should I quit that out? I try to be information dense...
And then there's the bullshit artists.
Just because we never had the option of a chisel before doesn't mean all chiselers are bullshit artists.
reply