Do you have any special insight here or are you speculating? I'm not saying that he should be free from criticism, but that we should try and have some empathy for people who try things even if they fail, particularly when they've offered their services to the community for free for the last 5+ years (much longer when considering node.js)
Ok but those government grants don't really exist today and what you're arguing for is zero sustainability for open source projects. This is certain to lead to the death of open source - there's not even the reputational pay-off any more if the only real consumer is AI.
People want open source software, but they do not want the compromises that come with funding it. When people try and fail then you get shitty blog posts like this one. It's sheer entitlement. I think the days of building open source tooling and expecting to be able to commercialise it are now completely gone.
These things are easy to say but just because someone has the title CEO doesn't mean they're automatically void of human feelings. I'm sure you understand there's a big gap between a Ryan Dahl and a Satya Nadella, despite them sharing the same job title.
Agreed. It is very easy to criticise if you've never been in the hot seat, and if you've never had to make tough decisions like this. As far as I can tell this person has never run a business with actual employees.
If Dahl had posted the typical layoff announcement people would be criticising that too.
This is a ridiculous article and reeks of insecurity at the top at Vercel. You cannot expect to reap the benefits of open source software without accounting for the costs.
I think a big part of why this discussion is coming up again and again is that people assume the way they are using AI is universal, but there's a bunch of different ways to leverage it. If you have an agent which runs within a product it usually cannot touch the outside world at all by design, you do not need an explicit sandbox (i.e. a VM or container) at all because it lives in an isolated environment. As soon as you say "we use CLIs not MCP" well now you need a sandbox and everything else that goes along with it.
If you can tell ahead of time what external connectors you need and you're already sandboxing then by all means go with CLIs, if you can't then MCP is literally the only economical and ergonomic solution as it stands today.
How are those CLIs being installed and run on hosted services? You'll need to sandbox them and have a way to install them automatically which seems difficult. How does the auth flow work? You'd need to invent some convention or write glue for each service. These are far more complicated than just using MCP, regardless of the benefits of the protocol itself.
no, it's all about auth. MCP lets less-technical people plug their existing tools into agents. They can click through the auth flow in about 10 seconds and everything just works. They cannot run CLIs because they're not running anything locally, they're just using some web app. The creator of the app just needed to support MCP and they got connectivity with just about everything else that supports MCP.
You can have a hybrid approach - deny access in that area by default but have a secure way to whitelist specific terminals for short periods (mission duration)
The issue with these LLM-targeting DSLs is that you have to waste a bunch of your context window explaining the grammar and semantics to the LLM, whereas they already speak existing programming languages because they've seen so much existing code. This usually negates the benefits of the DSL.
it is straightforward to build this for real, here is my nearly one-shotted tldraw clone from a couple of weeks ago, https://x.com/c_pick/status/2028669568403578931 - the implementation side never saw the code, only the spec (in reality it did see the tldraw code in its training data, but you can't escape that anymore)
This is satire, but I actually have built something that can do this extremely well as an unintentional side effect. I will not be building my business around this capability however
there's a whole world of AI tools out there that don't focus on developers. These tools often need to interact with external services in one way or another, and MCP gives those less technical users an easy way to connect e.g. Notion or Linear in a couple of clicks, with auth taken care of automatically. CLIs are never replacing that use case.
I don't doubt that CLIs + skills are a good alternative to MCP in some contexts, but if you're building an app for non-developers and you need to let users connect it to arbitrary data sources there's really no sensible, safe path to using CLIs instead. MCP is going to be around for a long time, and we can expect it to get much better than it is today.
When they seamlessly switch from English to Dutch I feel like I’m having a stroke: all the same intonation, the same accent, but nothing makes sense any more
The pattern matching example has a type Shape which is never referenced and this seems to conflict with the idea that you never write a type, am I missing something obvious?
I'm more interested in the general question rather than the specifics of this situation, which I'm sure is now incredibly common. I know it looked at those implementations because I asked it to, and therefore I will credit those projects when I release this library. In general though, people do not know what other material the agents looked at in order to derive their results, therefore they can't give credit, or even be sure that they are technically complying with the relevant licenses.
The other day I had an agent write a parser for a niche query language which I will not name. There are a few open source implementations of this language on github, but none of them are in my target language and none of them are PEGs. The agent wrote a near perfect implementation of this query language in a PEG. I know that it looked at the implementations that were on github, because I told it to, yet the result is nothing like them. It just used them as a reference. Would and should this be a licensing issue (if they weren't MIT)?
it was set up by a person and it's "soul" is defined by a person, but not every action is prompted by a person, that's really the point of it being an agent.