Those profiles represent thousands of hours of invested time. Having them deleted from the internet means they've lost all of that accumulated work.
When I answer questions in a public forum, helping the person who asked the question is only about half of the value I expect to get from my contribution.
Pepperidge Farm and the web archive remember. Most unfortunately, it has also remembered my most egregious mistakes. I am happy and embarrassed at the same time.
Granted, in the domain of tech support, the usefulness of answers is not as evergreen. But it's more about the curt, impersonal way they're cutting off a group of people who contributed a lot of value. Just abruptly muting everyone and then saying "this is all going away in a few days, kthxbye."
I wasn't a regular there beyond from occasional search hits. But presumably heavy users would want their contributions preserved in a way that's still useful for the type of people they wrote them for in the first place. An archive.org or torrent copy means they still technically exist, but not in a way that's helpful in a practical way.
It'd be like if Wikipedia suddenly closed down tomorrow -- prolific editors would take cold comfort from being told their contributions are still available to anybody who downloads an obscure multi-gigabyte archive file.
We must take the world as it is and not as we would like it to be. Apple’s hosting of it has come to an end, but there are trivial ways to continue to preserve and serve the information. It is what it is. I prefer defaulting to action instead of helplessness, other opinions will differ.
If someone wants to build a spiritual successor, build it on AT Proto to prevent potential loss due to corporate actions in the future. A PDS for storage, a post per topic/thread, etc. Due to the inherent open nature of the social rails AT Proto offers, this enables robust, open consumption of the data by future prospective consumers, humans and agents alike. I’ll cover reasonable infrastructure costs. It’ll all be ingested by the Internet Archive for preservation.
Broadly speaking, intentional effort must go into cultivating and curating systems in this regard. The platform must be open and sustainably operated, and contributors and curators must be valued for their thankless, tireless, unpaid work. Like Wikipedia.
It's ok, everything was ingested into model training. The ai companies save everything and give it back to us in the most accessible way possible, natural language.
"Harbor is currently in a private preview under Apple’s Claris brand"
There's a name I haven't heard in a long time! Claris (always an Apple subsidiary, since being founded in 1987) renamed themselves to FileMaker in 1998, but apparently they rebranded back to Claris in 2019.
This could actually be interesting for "regular" people. FileMaker was great in enabling non-IT people and SMBs to develop custom software for themselves. Think HyperCard with tables.
Some of that software has been in use since the 90s and still works. Adding AI to the equation will empower a lot of people.
However, FileMaker is not really targeted at software engineers. In fact using it as a developer will likely drive you up a wall. It's things that feel totally fine to non-devs but completely insane if you're used to something else. E.g. I remember having to click a thousand GUI buttons just to edit a few lines in a script once (regular users just "record" them through the UI). It did all work fine though, very reliable.
They added some more developer-specific features later, but it took a long time. E.g. editing scripts as text(-ish) only came in 2015 (FileMaker 14) and an actual programming language in 2020 (JS, FileMaker 19).
If they keep Harbor under the Claris umbrella, that is a nudge that they are doing it for SMB market instead of the consumer market and it will likely be a onerous subscription to use it.
FileMaker really could have had a moment when iOS devices took off since you could get a basically free native app just by having a database, but (I'd argue) got bogged down by poor pricing models. I would have loved to run it, but it's always been prohibitively expensive for anything not an enterprise, and now it's far too easy to spin up a CRUD API and call it a day.
"The other day I traced a picture of the Mona Lisa and I did it just fine, I am now a renaissance painter"
Now, substitute yourself with my robot:
"The other day my robot traced a picture of the Mona Lisa and I did it just fine, my robot is now a renaissance painter"
This is such a broken line of thinking, I can't even begin to understand it.
In this particular case I didn't imply that I had done ANY of the work (or even that the result was any good - the "just fine" was a judgement on the conversion from Three.js to vanilla JS.)
> Everything in this game is from scratch: models, sounds, textures. ~$550 at API pricing, ~2.7M output and 445M input tokens, heavily cached. Took 8 hours!
"You know, you should also build me a FPS. Insanely detailed quality pls, something that looks visually like it can keep up with AAA. Make it small in scope (like a tiny level) but otherwise impressive photorealistic graphics"
> Make a three js animation where yonkers stands up as a big mech (cool stand up motion) and stomps around manhattan and queens and Brooklyn, use openstreetmap mapping data
That index page should link to plain markdown versions of all of the documents, and should be designed for search with grep to find the right answers.
That way I don't have to install anything at all - provided my agent has the ability to make HTTP requests I can tell it "Look for tips on https://googlechrome.github.io/modern-web-guidance-src/skill..." and it will fetch the index, then navigate to the most relevant documents - no MCP or npm or installation required at all.
Aye. I like the idea, Simon. The token cost of the index is high enough I wouldn't suggest the technique for regular use but.. agree that for occasional users it should suffice.
It looks like the markdown has cross references that assume that the cli approach is used, it would be nice to separate the content from the tooling to access.
yeah that's fair. the infrastructure we are on isn't the most flexible (we will soon move to a newer more custom platform but that's a little way a way)
> That way I don't have to install anything at all
It feels that something like this would be the holy grail of agents. A small agent that has only the minimum necessary built in knowledge. The rest, it just retrieves on the fly when it needs (+ caching)
It’s like storing pointers/links instead of the contents
In reality that's pretty much what we got here. Very progressive disclosure centric. There's a 'install' command exists because the ecosystem doesn't have good cross-agent ergonomics for installing skills. (Which bums me out).
But yeah.. big corpus of valuable context × minimal agent footprint = happy place.
If created properly, skills are already something like that. You have a front matter summary always available to the agent. The agent can request the full skill content on demand, which might contain additional linked documents with details about APIs and schemas being used, deeper documents about niche subtopics, scripts to help with subtasks, etc.
I'm really sad about this. Val Town is a beautiful collection of ideas, but I get how building a sustainable business on top of those ideas (not-quite commodity hosting, since people need to commit to the Val way of building) is extremely hard.
I'm definitely looking forward to seeing the code in February when they open source it.
I'm not convinced the heading "Here's how I meticulously typed out and debugged code implementing an algorithm from a 2007 Microsoft Research paper" would have been any more interesting.
When I answer questions in a public forum, helping the person who asked the question is only about half of the value I expect to get from my contribution.
reply