Unfortunately I still look at them, too, out of habit: The project or repo's star count _was_ a first filter in the past, and we must keep in mind it no longer is.

> Good reminder that everything gets gamed given the incentives.

Also known as Goodhart's law [1]: "When a measure becomes a target, it ceases to be a good measure".

Essentially, VCs screwed this one up for the rest of us, I think?

[1] https://en.wikipedia.org/wiki/Goodhart%27s_law

Now divide the average SOTA LLM's training cost (or a guess, since these numbers aren't always published as far as I'm aware) by the number of users, or if you wanted to be more strict, the number of people it's proven to be useful for (what else would training be for), and it might not be so far off anymore?

Of course, whether it makes sense to divide and spread out the LLMs' costs across users in order to calculate an "average utility" is debatable.

[1] https://www.publicschoolreview.com/average-spending-student-...

(Please do correct me if this is wrong, again, I don't have the experience myself.)

[1] https://pkg.odin-lang.org/

[2] https://www.gingerbill.org/article/2025/09/08/package-manage...

Yeah, at the bare minimum these projects could also use something like portless[1] which literally maps ports to human- (and language model-)readable, named .localhost URLs. Which _should_ heavily alleviate assignment of processes to projects and vice versa, since at that point, hard-to-remember port numbers completely leave the equation. You could even imagine prefixing them if you've got that much going on for the ultimate "overview", like project1-db.localhost, project1-dev.localhost, etc.

[1] https://port1355.dev/

Work is still being done on how to bulletproof input “sanitization”. Research like [1] is what I love to discover, because it’s genuinely promising. If you can formally separate out the “decider” from the “parser” unit (in this case, by running two models), together with a small allowlisted set of tool calls, it might just be possible to get around the injection risks.

[1] Google DeepMind: Defeating Prompt Injections by Design. https://arxiv.org/abs/2503.18813

[1] https://arxiv.org/abs/2601.02671

But that's not provider-agnostic, which you mentioned earlier as one selling point of Emdash. :-)

Not-so-unrealistic use case, IMO: What if I want my orchestrator model to be, for example, ran locally due to some form of privacy concerns?

Prompt injection is _probably_ solvable if something like [1] ever finds a mainstream implementation and adoption, but agents not being deterministic, as in “do not only what I’ve told you to do, but also how I meant it”, all while assuming perfect context retention, is a waaay bigger issue. If we ever were to have that, software development as a whole is solved outright, too.

[1] Google DeepMind: Defeating Prompt Injections by Design. https://arxiv.org/abs/2503.18813

> Can you describe or offer any insight into the "significant IP" that you need to protect and defend?

The novel IP is having implemented and still implementing the browser APIs necessary for both Firefox and Chromium extensions to work in a Safari (Webkit)-based browser. See [1] for the significant progress.

> What threats from a larger company are you primarily concerned about?

Integrating said functionality themselves to offer another viable iOS browser, which Kagi is currently the only [2] offerer of (or another viable macOS/future Linux/Windows browser, although more than one exist there already).

[1] https://docs.google.com/spreadsheets/d/14IgSRVop4psUTgtLZlvY... (via: https://help.kagi.com/orion/misc/technical.html)

[2] Unless the EU steps up, all iOS browsers will continue to have to be Webkit-based with minimal, lackluster extension support. Not viable for anything beyond the most basic of use cases.

So I’m guessing that’s the reason for this “passive firing” method.

[1] https://www.brow.sh/

Take a look at what the Speedometer 3 test suite includes.

I still chuckled at Bloatscore, though.

Because I’m not disagreeing with your point, I’m actually not getting it in the first place. How does jumping around affect your selection count? Which motion(s) are you performing that larger quantities of text are getting "selected" in the first place?