Just tell the clanker to use modern practices poof fixed.

Jokes aside a lot of that bad code can be detected by static linting tools and gated on, making it impossible for any of those to reach main.

That is factually incorrect.

Help page from Kagi (I’d understand if you don’t trust it), fit for non-techie consumption. https://help.kagi.com/kagi/privacy/how-does-privacy-pass-work.html

So here’s the RFC, which defined the protocol in the first place (Kagi didn’t invent it, just implements it) https://www.rfc-editor.org/info/rfc9576/

As such they have absolutely no way of ‘deciding’ to look up a searchers account based on the token used.

That ofcourse does not reduce other ways anyone can track you like fingerprinting.

You seem to be misinformed. Kagi’s privacy pass cryptographically proves that you’re allowed to search, without having anything link back to your account. It doesn’t get more anonymous than that.

Best of all, that really is something LLMs are quite good at too. Aikido has a feature where you whitebox pentest your entire application.

To expand on this, using tokens as a unit of billing is quite reasonable as it is also the unit of (inference) cost for LLMs.

The inference is essentially nothing but a loop of “Hey if the first X tokens are this, what would token X+1 most likely be?” until the LLM says its done. Every single loop is a ton of math which, on ridiculoudly expensive hardware, uses electricity and produces heat. So its a combination of those costs, and then we haven’t even taken into account the cost to train the model.

We have a few dgx sparks in the office that are gathering dust right now because nobody wants to bother with them (and because IT doesn’t allow them on the network because Linux is scary so they’re a pain to get set up).

Matching the level of productivity of frontier models on the local models is possible to a limited degree (depending on the exact task), but takes getting used to. For the local models you have to lean into the fact that tokens are ‘free’ so its fine to burn a lot of them. (Whereas with frontier models the recommendation is to take a higher model for complex tasks because a lower would take more tries to get it right)

MaM tightened their invite forum requirements quite a bit. They ‘found out’ that a ton of users were just there to use it as a springboard.

Bookorbit has a request feature since somewhat recently (tested it a bit and with search on MaM for English books I’ve gotten a 100% hit rate so far)… However its probably the project you mentioned as vibe coded and the dev has some controversies (they also made booklore which imploded spectacularly). It also has a ton of great features to sync with ereaders etc. I’ve been running it to manage a pretty big library and its been pretty solid.