If it were intended to be a direct alternative for the biggest use case, I think it would be more like Cloudflare Workers and Durable Objects. However, I think it's an alternative for a lot of uses of those two things. For a lot of uses of them, likely most uses, they are overkill.
So where it's overkill, this is where Celld is a good fit. It's a 100% open play, despite mentioning three hosted APIs: S3, Cloudflare Workers, and Durable Objects. The thing is, that Deno tried making similar ones. Deno Deploy is analagous to S3, and Deno KV is analagous to Durable Objects. However, with Celld the only dependencies are being able to run a binary and some S3-compatible storage. Cloudflare provides S3 compatible storage, but this README doesn't mention that, except in an example. Perhaps Ryan is leaving the door open for Deno to be acquired by Cloudflare.
There is also qm with smol machines. I found this out the long way, by looking at the contributors to qm at https://github.com/yc-software/qm where I found BinSquare, the founder of smol machines. Then I found a tweet about a public instance of it where I could try out having it code something agentically - I'm in the replies here: https://x.com/binsquares/status/2083305704274976819
I guess the lock-in is to Cloudflare Workers, which is limited to JavaScript. I would in fact look into projects that are built around MicroVMs and WebAssembly. It seems Buzz would be happy to use smolmachines, or whatever. You'd have to roll your own permission system, but smolmachines would at least take care of being able to use stuff within an app, by offering persistent, portable containers.
Actually I think now I can finally say why this sandstorm.io with Cloudflare OS has lock-in. The promise is "you can pretty much go wild" and that you can hand it off to non-technical people to do that. Much as you squint, there is not a sophisticated access control system available to self-hosted users. There's a framework for building a sophisticated access control system, but that isn't the same as having something open source that you can self-host and let non technical users go wild.
However, this is cool. I just agree with you that Buzz sounds more interesting to me as someone who was into Sandstorm.
Ah, that changes the amount of work and the reward in the equation for attempting to self-host Cloudflare OS. And I knew that I could run WebAssembly manually inside of JavaScript, but it seems to be runnable directly too. What would help me to know further is how Cloudflare OS integrates its access control in that open source project, and if it is conveniently available to WebAssembly, Python, or Rust workers.
To say that you're building agents, is based on a way of viewing things that isn't at all pervasive. Some might say you're building a customer support chatbot. To talk of building agents as a common activity makes sense if you use LangChain I guess, where its title is "Open Source AI Agent Framework | Build Agents Faster". But for instance, YC just released qm, and in its README it talks about customizing the agent, which is quite a bit different from just casually dropping the phrase "I'm building an agent". https://github.com/yc-software/qm
Not sure what you are trying to say but thanks for reminding me about qm, it has some cool features.
My MindRoot framework had some of qm's main features awhile ago though. I do try to use it to build solutions by customizing rather than from scratch when possible. But a lot of clients or potential clients don't like that idea even though it's MIT. They want some that has clearly been invented by them as a new programming project.
I actually turned down a project last year from someone who wanted me to start over in LangGraph -- he had already decided on it before he knew about my thing.
The most recent project I have been using MindRoot and building up the voice capabilities so I can now handle voice agents end to end including SIP.
But on that website now I try not to emphasize my framework at all for most proposals. You don't have leverage on Upwork. And also with code generation it isn't a critical point necessarily.
Why are you looking for projects on upwork if you know they don’t pay well and that you don’t have leverage? That sounds like a pretty bad place where to find contracting projects
Please recommend somewhere else. I have started on LinkedIn but especially without much time and having so much experience being shortish Upwork contracts it's a hard sell without lying on my resume and so I am having to be careful where I spend my time.
The biggest advantage of Upwork is I have a track record there and there are tons of RFPs. Other places usually don't have RFPs and are going to look down on the Upwork record.
But I appreciate any ideas for places or people to look for work. My email is in my profile.
I am not sure about funding for rent if I don't pick something up this week.
Fortunately the site is right next to the title, and so HN regulars can see it's a Simon Willison post about it. And like many expect, it isn't merely reporting, but offers interesting thoughts on it, including some not in the HN discussion you mentioned.
> Fortunately the site is right next to the title, and so HN regulars can see it's a Simon Willison post about it.
With exactly the same title? Regardless it isn't the original post and that is what most are here for. I am just saving them a click to go to the source article.
> And like many expect, it isn't merely reporting, but offers interesting thoughts on it, including some not in the HN discussion you mentioned.
It is reporting on the blog itself. In fact, the whole post could have been a comment under the actual post in [0] where the comments shows more than one perspective. That goes both ways.
But it is far more better to have lots of other commenters telling us what they think with the full context of the article, rather than just one perspective with tiny excerpts from the source.
I disagree. "Benefit society" means something that can't be defined or tracked so easily. And consumer behavior is heavily biased by things that aren't optimized to benefit society. I have in mind this book, Hooked by Nir Eyal: https://www.nirandfar.com/hooked/
We should try our best to improve our society. Sometimes that will mean doing things that are economically inefficient. Your example of Stanford professor Nir Eyal is an excellent illustration: by advising corporate managers and product designers how to fulfill their role in our economic system more efficiently, Nir Eyal made our society worse.
We should expect more from our elite professors. Nir Eyal should've known better than to make a career out of studying how deliberately to addict users. But we should also expect our professors, politicians and policymakers to understand the basics of our economic system and to understand when a proposed change to our society sounds good or feels good, but has severe adverse effects on economic efficiency that outweigh the societal benefits. Those aren't the only proposed changes we should avoid, but they form an important class of them.
I think the brand Clawd belongs to OpenClaw now. It didn't start there but it landed there, until Anthropic tried to kill the fun. Anthropic hardly uses that name, it's mostly an anonymous mascot.
Since Anthropic clearly maintains copyright over the mascot itself (though it is so simple it feels like a stretch to me) I prefer not to see it referred to as Clawd...
Edit: props to Anthropic for bringing more attention to Claude Shannon
Edit 2: this repo does show very well the dimensions of the Claude Mascot at rest - it's only 12x8 https://github.com/afspies/ClawdMoji#the-pixel-grid It's both impressive and seems independently discoverable. How many symmetric 12x8 patterns are there?
It's something to avoid for everything. They've gone further with nastiness than the other FAANGs IMO. Though alternatives may be hard to see, they exist, including for PyTorch. In many places it's zero sacrifice like with React.
The request would need to be done from their service, so as not to expose the API key, and because it just makes sense. They could probably directly proxy it and Wireshark couldn't catch it, due to everything being HTTPS. But people could probably catch it by decompiling, so it would make more sense to have the server make the request as part of a GLM request. Not that I think this is plausible - I'm not sure.
So where it's overkill, this is where Celld is a good fit. It's a 100% open play, despite mentioning three hosted APIs: S3, Cloudflare Workers, and Durable Objects. The thing is, that Deno tried making similar ones. Deno Deploy is analagous to S3, and Deno KV is analagous to Durable Objects. However, with Celld the only dependencies are being able to run a binary and some S3-compatible storage. Cloudflare provides S3 compatible storage, but this README doesn't mention that, except in an example. Perhaps Ryan is leaving the door open for Deno to be acquired by Cloudflare.
FWIW here's an old Deno blog post comparing Durable Objects to other stuff: https://denoland.medium.com/deno-kv-vs-cloudflare-workers-kv...
reply