Neither RAG nor loading the docs into the context window would produce any effective results. Not even including the grammar files and just few examples in the training set would help. To get any usable results you still need many many usage examples.
My own 100% hallucinated language experiment is very very weird and still has thousands of lines of generated examples that work fine. When doing complex stuff you could see the agent bounce against the tests here and there, but never produced non-working code in the end. The only examples available were those it had generated itself as it made up the language.
It was capable of making things like a JSON parser/encoder, a TODO webapp or a command line kanban tracker for itself in one shot.
And yet it works well enough, regardless. I have a little project which defines a new DSL. The only documentation or examples which exist for this little language, anywhere in the world, are on my laptop. There is certainly nothing in any AI's training data about it. And yet: codex has no trouble reading my repo, understanding how my DSL works, and generating code written in this novel language.
If you want to section hike it, its entire North American part is covered by the Eastern Continental Trail (ECT), which some people (very few, as in a tiny fraction of all A.T. thruhikers) thruhike it in a single calendar year.
Other than the cold start problem which isn't discussed (what's the userbase size in Gaza?), the main argument for Bitchat (or any other off-grid network such as Meshtastic, Briar, etc.) in Gaza when mainstream E2E encrypted messaging apps already exist and are widely used, is to not be dependent on Israel for cell service.
While I do really like the idea of off-grid networks in general but for this use case, is it really that hard for a state actor to jam Bluetooth (or all ~2.4GHz communication) on a large scale?
I feel like the idea here is cute; but does it realistically work at scale? Of course, a messaging app like this—if it's going to work anywhere, is going to work in Gaza, one of the (at least formerly) most densely populated areas in the world. But bluetooth was not designed for this type of communication whatsoever; phones can only establish bluetooth connections between devices at the very most 100ft under the most ideal conditions; and is probably much lower than that in practice.
Even if people are living in open-air conditions I can imagine messages getting stuck or being delivered very late; especially at night when there may not be a lot of human movement. How well does this actually work in practice?
A disaster, cyberattack, or prolonged blackout could take down cell towers in a broad area, this could be useful in that case. And in a civil emergency a government may be able to shut down cell towers centrally, but not have the resources to jam the entire country.
Tens of thousands of users? Globally you mean? I doubt it's the user base size in Gaza but if that is actually what you meant, where did you pull that estimate from?
reply