You're right, that snippet was ai-generated and I forgot to action one of my todos to fix that snippet. This was negligent on my part, and I hope you'll forgive me.
We're fixing that right now, thank you for the correction!
This is pretty fair: in claude code, I have the github mcp server installed, but the agent actually prefers to use the CLI. There's also other advantages too, such as incremental discovery of subcommands for more complex CLIs. Certainly agents already don't have a problem using CLIs.
That said, this doesn't fully work in environments on websites like claude.ai. Perhaps you could have an org-wide Dockerfile or something that opens every time you start a chat which gives it MCP-like capabilities, but that sounds more complicated in many ways than what MCP does. There's also more problems that MCP solves, like with Prompts and Sampling (which are pretty under-used at the moment), and there aren't great analogs for that in the CLI world.
Also developers like you and I might find it trivial to install CLIs, set up auth, and open an agent locally, but this isn't widely true. As an example, at Stainless we have non-engineer folks who ask questions like "who are the most interesting people who have signed up yesterday", and with the right MCP tools wired to claude.ai, claude actually does an excellent job of answer these kinds of questions, all in the browser. This was all without a doubt possible before MCP, but MCP reduces the friction enough, such that it becomes worth-it/easy-enough to develop these tools.
What you are actually saying is that you don't have a data platform with reporting and prefer using your own product because you designed your user tier to have an MCP server, which is kind of an ourobouros.
Hmm? We have a REST API, CLI, MCP server, and SDKs that all offer the same data/functionality.
MCP is for AI agents, the CLI is for one-off commands by devs who like to poke at things or CI scripts, the TypeScript SDK is for production software written in TypeScript, etc etc.
Was there something we're missing from the "data platform"? A SQL interface?
> Maybe it was because OpenAI announced they would start to support MCP in their tools ? [0]
Author here, I assumed this would be the reason too, but the timelines don't really match up. Momentum was already strong by the time that OpenAI adopted it. And it's an educated guess on my part, but that's also probably why they adopted it in the first place.
Some sources point to the MCP talk at AI Engineer being the turning point (and the timelines match up), but like with all viral studies the answer is pretty complicated and multi-faceted, rather than having a single cause.
> Perhaps I'm being too harsh with the author, but this article definitely gives me vibes of "AI slop".
I think it's fine to be harsh! I don't like AI slop either but unfortunately this article was mostly handwritten, so it's just a skill-issue on my part. I'll try to do better next time
While true, I think people underestimate the bad network effects of being the top search engines causing adversarial development with people optimizing for your specific search engine algorithm ultimately making results worse.
That's a pretty severe mischaracterization of intersectionality in general. Intersectionality refers to the fact that you can't analyze human experiences as linear terms (being black, being a woman) and that you must consider the effects of being some combination of categories. As an example, intersectionality claims that being both black and a woman brings separate challenges than the additive combination of being black and being a woman.
That's all there is to intersectionality, any conclusions you make beyond that are your interpretation of intersectionality, not the general consensus of the "far left".
That's really not "all there is" to intersectionality. You are repeating the motte-and-bailey of far-left ideologues wherein you fall back on the official/original definition of the term, conveniently ignoring that its meaning has changed over time, and has been coopted.
To be clear: I'm being charitable in my interpretation, and assuming you are not intentionally doing this.
https://newdiscourses.com/tftw-intersectionality/ clarifies how the notion of intersectionality is generally interpreted in a Foucaldian way by most people who engage with it. This "interpretation" is not just parent post's but widespread enough to call it a consensus.
You're going to quote James Lindsay, the guy who refers to critical theory as 'race marxism'? This source is so biased Ma'at's feather never had a chance.
Lindsay is an academic and his arguments are out there for you to rebut if you wish. Attacking his character doesn't dismiss his ideas even though the left wishes as much.
Don’t play coy. Intersectionality is a framework for dismantling the status quo. From wikipedia:
> Crenshaw used intersectionality to display the disadvantages caused by intersecting systems creating structural, political, and representational aspects of violence against minorities in the workplace and society.[15] Crenshaw explained the dynamics that using gender, race, and other forms of power in politics and academics plays a big role in intersectionality.
It’s not just the idea that multiple identities can be at play at once. It’s a tool in the postmodern toolbox.
Nobody even needed intersectionality to explain the idea that humans can’t be reduced to a single identity (that’s just common sense) until 3rd wave feminists convinced us as much in the first place.
Lots of businesses have a front of the house (customer-facing roles) and a back of the house (warehouse, etc.). In the South, many businesses only hired white people in the front of the house, and only hired men in the back. You argue that it's "just common sense," but it was widely accepted that these practices were neither neither racist nor sexist because the business does hire some women (in the front) and some black guys (in the back). But if you were a black woman, you were shit out of luck.
It might be obvious now, but it took intersectional thought for people to begin to acknowledge these less overt forms of discrimination.
> It might be obvious now, but it took intersectional thought for people to begin to acknowledge these less overt forms of discrimination.
It really didn't. I was raised in conservative evangelicalism and was never exposed to "intersectional" thought, but it was obvious to me that someone in multiple disadvantaged categories had it worse than someone who was only in one of them.
It was also obvious to me that any hiring system which a priori debarred a given category of people at the start was discriminatory.
Intersectional thought undoubtedly has helped some people figure these things out, but it really isn't necessary to understand these problematic behaviors and situations.
I have a huge bias towards functional programming, one core tenet of which is immutability. When I was going through the official svelte tutorial I read this[1] paragraph:
> Note that interacting with these <input> elements will mutate the array. If you prefer to work with immutable data, you should avoid these bindings and use event handlers instead.
Which left me with the impression that svelte's functional story wouldn't be that great. Though I did still finish the tutorial.
As my first project I tried to migrate one of our static websites to svelte with sveltekit. It didn't really feel like I was doing something different than when I was using Vue3/Nuxt3, so I might as well stick with it. I understand that the technical tradeoffs are different, svelte is compiled and has no runtime after all, but the developer experience pretty much feels the same.
You're right, that snippet was ai-generated and I forgot to action one of my todos to fix that snippet. This was negligent on my part, and I hope you'll forgive me.
We're fixing that right now, thank you for the correction!