syndeo

I for one run a small Scripture-study web app that makes use of this on Chrome browsers when available to provide summarizations of long commentary articles. I'm also looking to use it to power topical search.

I allow free open access to the content, as blocking it behind an account signup doesn't sit right ethically—it should be open and free for everyone.

The issue there is that there's no way to easily secure the API from being hammered by bad actors. (Due to the often-controversial response many have to Scripture, apps like these draw special kinds of negative attention.) You can set rate limits, but people can still abuse those, just to try to burn your money. I can get by for free (or relatively cheap, fully paid out-of-pocket as none of this is monetized) on Vercel/Netlify/etc, but inference is expensive, and a prime target for those trying to cause trouble.

If in the future the web exposes local "foundation" models that web apps can assume are present, that would open up great possibilities like these for indie devs like myself. Being able to offer useful and compelling features without worrying about abuse would be nice. That's my point.

Totally fair. Depends on how it's used, really.

If it's to allow the web apps I use to work with more privacy, or to enable smaller/indie players (that can't easily afford to burn a bunch of API tokens for every user) to offer some basic AI-based features in their web apps, then I'm all for that.

This is the whole appeal of Apple's Foundation models on iOS too.

It’s actually really useful for web devs to have access to a local model. Whether or not browsers should bundle their own rather than using the system-provided model(s) is up for debate, however. For the time being, though, Google does have some of the better small ones.

Furthermore, users aren’t going to want to have to wait for an extra thing to download before their web apps can use AI.

That’s the thing… Without context of why, users probably wouldn’t want a 4 GB download. But they do want their web apps to work properly. When there’s a specific use case they’re interested in, they will want to have it, and they won’t want to wait.

Once you get the compartmentalization working well, and “all” of the vulnerabilities are out of it too, of course…

But even then you’ll have users putting things in the same compartment for convenience, rather than leaving them properly sequestered.

MAN I remember Slashdot… good times. (Score:5, Funny)

Wouldn’t that be wild? I don’t know that the Naomi version runs on it yet, but that would probably be a decent place to start.

At least as a reference implementation for most of the engine!

Definitely sounds like clickbait, but this is a genuine problem I've been facing on my more complex projects. I was trying to work around it by making lots of .md files that contain context for various components of the app, as well as ones that "statefully" represent our steps along larger refactors, allowing things to persist across sessions. But that requires the hygiene/discipline of remembering to have the model update those.

Now… how much of our tiny context window does this eat up? And what if we're working on something very different from the previous tasks; might that irrelevant context risk confusing the model?

Also, how does this work if I work on multiple projects across different directories? Will it know to not get those mixed up?

Wanting to "live" in a Lambo-shaped server rack is genuinely cute, ha.

> LAMBO OR WE WALK!

The nerve, haha. This is hilarious.

>When FileVault is enabled, the data volume is locked and unavailable during and after booting, until an account has been authenticated using a password. The macOS version of OpenSSH stores all of its configuration files, both system-wide and per-account, in the data volume. Therefore, the usually configured authentication methods and shell access are not available during this time. However, when Remote Login is enabled, it is possible to perform password authentication using SSH even in this situation. This can be used to unlock the data volume remotely over the network. However, it does not immediately permit an SSH session. Instead, once the data volume has been unlocked using this method, macOS will disconnect SSH briefly while it completes mounting the data volume and starting the remaining services dependent on it. Thereafter, SSH (and other enabled services) are fully available.

Now THAT is a welcome change!

> run WASM on bare metal

Heh, reminds me of those boxes Sun used to make that only ran Java. (I don’t know how far down Java actually went; perhaps it was Solaris for the lower layers now that I think about it…)

Thank you for the quick fix! Your steps worked perfectly.

In any case, I'd like to add that I'm hoping an ACP adapter for OpenAI Codex is in the works; I've grown pretty fond of GPT-5, and would like to be able to tap into my existing ChatGPT Plus subscription; I'd rather not use API pricing at the moment. I prefer using Claude Code vs directly hitting the Anthropic API for the same reason.

Heck, an ACP adapter for Cursor CLI (itself based on Gemini CLI, right?) would even be useful; as that would also let me pick GPT-5.

That's crazy. I knew Google's would be a lot bigger, but DANG.

True, but at least in prison you're (usually) fed… which may NOT be the case if you're fired from your job, put on a list, and blocked from the industry.