Download all of Wikipedia on your phone
practicalbetterments.com
practicalbetterments.com
The thought that I used to spend $.50 a game and now I can hold it in my hand for 4 times that.
Digital hoarding is a real thing
reddit.com/r/DataHoarder
Not to say that your point isn’t well taken. One does tend to keep stuff after a long overnight download, and old habits die hard. And I do have a local copy of Wikipedia…just in case.
<|im_start|>user
What is this sign about?\n<image>
###
<|im_start|>assistant
The sign is about bullying, and it is placed on a black background with a red background.
###
Step one in this daydream is always "Crap, no internet for 100 years -- if only I had all of Wikipedia cached".
Check! :)
Step 2 of course is figure out how to fashion some sort of charging system so my magical godlike pocket super abacus continues to function after ~days, but I'm making the bold assumption that somewhere in the annals of Wikipedia I can figure that out.
It'd be nice if there was a curated downloadable subset of Wikipedia pages for that kind of purpose. (Time-traveler in past, stranded/post-apocalyptic survival, history pages but only the text parts.) Even if only mundane events occur, it also represents a certain cross-section of user-interest.
That said, one more daydream item to add to the pile: "What if I was somehow lost in space, what useful information could I provide for maybe locating my home-planet again?"
____
Without Wikipedia, the best I can think of are notable conditions that could help them filter existing records, often using ratios to avoid having to define measurement units, ex:
1. It's the 3rd planet from the Sun, the majority of it is covered with water, etc.
2. It has an unusually large single moon of 1/6 its mass.
3. The 5th and largest planet in the system has a little over 70% of all the (known) planetary mass.
4. The 5th planet is 5.2x further from the Sun than my 3rd planet.
5. The 6th planet still has notable rings which haven't decayed yet.
With Wikipedia, perhaps I could tell them about pulsar maps or whatever. [0]
[0] https://voyager.jpl.nasa.gov/golden-record/golden-record-cov...
Locating the Sun from an unknown position in space, especially if you're many lightyears away, would be a complex task. Here are some strategies you could use:
1. *Spectral Analysis*: Every star has a unique spectrum, and the Sun's spectral signature is well-documented. If you have the capability to perform spectral analysis on nearby stars, you could compare their spectra to that of the Sun. This, however, assumes you have a database of stellar spectra, including the Sun's, for comparison.
2. *Position of Known Stars and Constellations*: By observing the position of known stars and constellations, you might be able to estimate your location. This becomes more difficult the further you are from Earth, as the relative positions of stars change with distance, and familiar constellations may become unrecognizable.
3. *Parallax Measurements*: Parallax is the apparent shift in position of an object when viewed from different perspectives. Measuring the parallax of nearby stars compared to more distant background stars could help you triangulate your position. Knowing your position relative to the Milky Way galaxy would be essential in locating the Sun.
4. *Galactic Landmarks*: Identifying key features of the Milky Way, such as the galactic core, spiral arms, or specific nebulae, could help orient you within the galaxy. The Sun is located in the Orion Arm, about 26,000 lightyears from the galactic center.
5. *Radio Signals*: If your ship can detect radio signals, it might catch broadcasts from Earth. The Sun would be in the general direction of these signals. However, depending on your distance, these signals might be very weak or non-existent.
6. *Automated Stellar Navigation Systems*: Use any advanced stellar navigation systems on board. These systems could automatically identify stars and calculate your position relative to them.
7. *Consult Star Maps and Databases*: If your ship has a database of star maps, you could use these to match up visible stars with known stars and work out your position relative to the Sun.
8. *Communication with Earth*: If communication with Earth is possible, getting assistance from ground-based observatories or space agencies would be invaluable. They could provide information based on your last known position and trajectory.
In the good old days of USB 2 I'm sure you can figure out how to get a stable-enough ~5V power supply that would charge the smartphone.
With USB-C you'd need to reinvent IC manufacturing and figure out a needlessly-fragile and overcomplicated protocol before the phone would even accept any power. Yay for progress!
You can probably provide at least 2.4A 5V on USB-A, just like providing 3A 5V would be fine with USB-C.
For a USB-C sink, you don't even need any resistors beyond that, let alone USB-PD. For a USB-C source to be able to charge a legacy USB-B sink, all you need is a single 56 kOhm resistor.
* Offline Map - The times I need a map and I am offline are strongly correlated. * Stardew Valley - Great game, pay only once, play offline, no ads.
Wikipedia does sound cool though. Maybe I'll trial one of the reduced size versions.
Completely offline, shows more info about the landscape than Google/Apple Maps, especially for hiking, has almost all businesses, has driving directions.
it's very rewarding when you see your changes being used by other people and apps
I do contribute to OSM, but day to day I find Google Maps + Alltrails + Trailforks to be more practical (all paid, closed source, but high quality data).
Google Maps also has free offline tiles. Those other two have paid offline maps, but it's worth it to not have to always wonder if your map is accurate.
When your phone can “hear” a cell tower (and thus thinks it’s online) but doesn’t have enough signal to get any data, apps like Google Maps and Gaia will often hang instead of showing you the downloaded map data that’s on your phone.
Put your phone in airplane mode to fix that behavior.
It’s a sad indictment of the current times that this isn’t completely standard.
I upgraded my wife's iPhone X to a 15 non-Pro, maxed to 512GB, but she has so many videos I doubt the ZIM will fit. I myself will keep my iPhone 12 until it either breaks or they no longer provide security updates for it. Not everyone changes to the latest iPhone.
Didn’t find it on a superficial search.
Especially if it could also cite sources.
You would have an hallucinating make-up-some-fake-facts machine on your phone.
I don't think that's definitely true, if you build the system around it well. It would look something like this:
1. User asks a question. LLM extracts key concepts from that question to use as search terms.
2. LLM triggers a search of Wikipedia, getting back snippets of pages, each with their page identifier.
3. LLM is fed those snippets along with the user's question and instructions to cite pages that it uses content from.
4. LLM generates a response which includes formatted citations. This response may be complete garbage, but...
5. Your code can at least confirm that the citations correspond to the pages that you fed into the LLM.
I've seen this approach work well with larger models. The open question is if it could work with smaller ones.
The 7B models (Mistral and its variants in particular) are getting VERY effective. I'm confident they could mostly-work for the above sequence... and you can just about run a 7B model on a phone.
The bigger question for me is if you could get this to work with a 3B model, since those are much more mobile-device friendly than 7B.
LLMs on mobile phones can be surprisingly capable. I've been having fun trying out this one on my iPhone: https://llm.mlc.ai/#ios
Getting that to work with a local copy of Wikipedia - where it can essentially run a "search_wikipedia(...)" function any time it needs extra information - would definitely be feasible, using this pattern: https://til.simonwillison.net/llms/python-react-pattern#user...
I think it would need to use regular text search though - you could try calculating embedding vectors for the whole of Wikipedia but even with a small embedding model I doubt you could fit those on the device, they'd take up too much space.
Maybe impractical, but seems like it could potentially be more seamlessly integrated. Keeping in mind:
- Many models already include WP in their training, at least parts of it.
- The parts that are missing or a subset of what’s missing could be supplemented via finetuning.
- Data is commonly compressed about 100x during training (it’s lossy) so the total size might still run on a phone.
You’d then have a fully capable LLM, but enhanced to be comprehensively encyclopedic.
The subdivisions the app provides isn't enough, or at least I was using it wrong. For example, trying to download the lighter versions of the Geography section only seems to offer combinations that ultimately leave you without much usable information (i.e Paris only providing the introduction text and not the content from the later sections) unless I go for the much larger size.
https://aarddict.org/ (available on F-Driod)
I hope they update it.
> Kiwix also allows you to download subdivisions of wikipedia — like the top 1 million articles at 43.53GB
I’d think the good ol’ Page rank would be a better metric for deciding which ones to prune.
Might be better to ignore certain topics you know you're not interested in. (That way if there's no result, you know there's either truly no result, or that you don't care anyway because you're not interested.)
Or perhaps most effective for the size goal would be just to cut images. Perhaps selectively include them depending on category - e.g. maybe you want them for science & technology categorised articles (diagrams) and geography, but can do without otherwise.