I think neuro-symbolic AI has a lot of potential here, since small models can handle a lot of conversational inputs, while relying on wired-in solvers for more complex symbolic math/computation needs. https://jjd.io/posts/swollm-bbh-leaderboard.html
For most actual emergency scenarios, a device that focuses on storage of large amounts of prepared normal reference material [0] will be wayyyyy cheaper, durable, portable, and able to run without being constantly plugged into a still-normal electrical grid.
In contrast, imagine spending the money to build a beefy LLM-running computer with good GPU/RAM, and mothballing it to depreciate, unused, in a "safe" location for the big earthquake/flood/etc. If the disaster strikes and you dig it out, how will you power it? If power is 20 miles away on the other side of the mountain, are you going to carry it on your back, or are you going to carry water to live? If you do carry it to an enclave, are they going to let you run it when it cuts into light for surgeons or heat to sterilize water?
This is couched in prepper nonsense, but it's got LLM, WikiPedia, maps, etc. A bunch of genuinely useful stuff to keep on a USB stick or whatever: https://www.projectnomad.us/
But, the current model you really want for an emergency kit is Gemma 4 12B QAT 4-bit. At ~7GB on disk, it's small enough to run on a tablet or any modern computer, slowly if you don't have a GPU or modern Apple silicon, but exceedingly smart for its size, excellent vision capabilities, good tool user, surprisingly good reasoning.
I've been mulling over a good use of a large philanthropy spend in the next decade, and I would love to build a bunch of hardware "oracles" that include an LLM. Ideally solid state, visual/audio, solar + usb-c, so, good in a lot of doomsday scenarios as well as just out hiking. It's a fun thought experiment. I imagine making like 1 million of them, they could be sold and genuinely useful, but also given away; once owned, you could use them, or store and put in an emergency box, bury next to the 10k year clock.. a lot of possibilities.
They want to ask the iOS Foundation model (frontier on device intelligence for something small) for instance about emergency procedures and life-saving info. I wouldn’t trust that model with much at all though. More likely to find what you need from miniature survival guides.
99% of the model "work" (meaning the connection to your computer) is just spinning a spinner - something that makes me want to wrap it with a mosh shell so I can just keep moving from network to network.
I feel that would be handy in all sorts of situations when networks are down.
For most actual emergency scenarios, a device that focuses on storage of large amounts of prepared normal reference material [0] will be wayyyyy cheaper, durable, portable, and able to run without being constantly plugged into a still-normal electrical grid.
In contrast, imagine spending the money to build a beefy LLM-running computer with good GPU/RAM, and mothballing it to depreciate, unused, in a "safe" location for the big earthquake/flood/etc. If the disaster strikes and you dig it out, how will you power it? If power is 20 miles away on the other side of the mountain, are you going to carry it on your back, or are you going to carry water to live? If you do carry it to an enclave, are they going to let you run it when it cuts into light for surgeons or heat to sterilize water?
But, the current model you really want for an emergency kit is Gemma 4 12B QAT 4-bit. At ~7GB on disk, it's small enough to run on a tablet or any modern computer, slowly if you don't have a GPU or modern Apple silicon, but exceedingly smart for its size, excellent vision capabilities, good tool user, surprisingly good reasoning.