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.
ah yes the common rebuttal of "but this doesn't exists, so I want the boot to keep stomping on my face. Please don't do anything different! The boot is kinda nice actually now that I sustained enough nerve damage."
Grants are a very effective model of support, it seems to work for entire industries + professions around the world. Even better when there is a body of professionals working democratically to decide which people should be awarded the grants.
Just because you have a failure of imagination doesn't mean others do.
Bad faith reply. The government grants do not exist, it's not a failure of imagination, I too would like to live in that world, but we don't and aren't likely to any time soon. And even if we did, do you think that Deno would have been likely to receive a grant? I do not.
You are barking up the wrong tree. Ryan can't do anything to make government grants for this kind of work exist.
It would be a huge public service if you could get more public support for open source. Maybe you could do it instead of criticizing Ryan!
Some public support for this kind of work already exists, especially for the Python science ecosystem, but nothing that comes close to "competing" with VC for a project like Deno.
You should be the change you hope to see in the world and make this happen!
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.
Well the people who get laid off also have feelings, not sure why we should care more about the ceo's feelings so much that we shouldn't criticize them
I'm not saying that we should care more for the CEO, but that we should have empathy for someone who is, ultimately, an engineer who built something and gave it away for free, watched everyone else around him get rich off the back of his hard work, and then tried to do something worthwhile again and still chose to give it away for free. There's a lot of immoral CEOs out there, I'm yet to see evidence that Dahl is one of them.
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)
> Do you have any special insight here or are you speculating?
I'm trying to understand why you carve an exception for this one individual.
When I worked in restaurants, the owner and I had a very interesting conversation after hours, and with beers, about his thoughts and feelings being responsible for the well being and livelihood of everyone that worked there. It was a positive moment, I thought I had a great boss, I work my ass off for him.
A year later I found he was trimming hours off of my paycheck. I quit on the spot. Months later I heard he did the same to the waitstaff tips and it wasn't much longer before it all fell apart.
People can appear very different publicly than privately, and they can change over time.
The reverse is true: asshole bosses who do right by workers quietly. Sometimes they're public assholes and privately terrible though. But sometimes (perhaps very rarely) they're openly caring AND do the right thing behind curtains.
I'm not saying anything groundbreaking here. Humanity is complex and varied.
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.
Right but if you read that page you quickly come to the quote "Parliament can make or unmake any law". Technically there is judicial review now, so there is some restrictions, but not like in a USA style constitution.
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.
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.
Write better CLIs for the agents of the less-technical people. The MCPs you're talking about don't exist yet either. This doesn't seem complicated; MCP seems like a real dead end.
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.
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.
> ...people assume the way they are using AI is universal
This is what led me back to MCP. Our team is using Claude CLI, Claude VSCX, Codex, OpenCode, GCHP, and we need to support GH Agents in GH Actions.
We wanted telemetry and observability to see how agents are using tool and docs.
There's no sane way to do this as an org without MCP unless we standardize and enforce a specific toolset/harness that we wrap with telemetry. And no one wants that.
Sure. But if you geoblock all use on Russian controlled land, you're also blocking Ukrainian use on Russian controlled land. I have no idea if that would cause issues or not, but it's not that far fetched to imagine it might.
I know this is a meme but for those at home the whole point of a war is to cross over the front line into the opponent's territory and capture it. If your comms are disabled when you cross the front you can't really fight. So "just disable Starlink within Russian territory" does not solve anything.
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 isn't Russians using Starlink inside Russia (they have other option, e.g. wired system, etc. there); the issue was their using it for drones and other combat operations inside Ukraine (including Ukrainian territory presently held by Russia).
The point is that in order for Russians to use Starlink in combat operations in Ukraine, they first have to import them to Russia. All non-whitelisted Starlink terminals entering Russia should be immediately bricked to prevent this. It's an important part for denying Russians the use of Starlink.
It's beyond sickening what none of you even bother with the idea what a civilian service should not be used by the military, especially in the zone of the conflict - by any side.
SpaceX is a privately-owned defense services company. Their #1 client is the United States. Their launches out of Vandenberg occur because the United States Space Force allows them to happen.
Are you on their board? Who are you to make the call that the product they are offering is a "civilian" (only?) service?
It knows this because it knows where it isn't. By subtracting where it is from where it isn't, or where it isn't from where it is (whichever is greater), it obtains a difference, or deviation.
I think what's actually funnier is that the satellite shooting the laser has to know where the terminal is with pin point accuracy too. So it's pretty easy to cut off targeting to a vast chunk of the planet.
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)
I wonder about this training data. There's so much profit from open source code in training data, actually the most of the code it was taught was open source, shouldn't it be then free? Or at least open weight?
reply