My unlock in genealogy research was using https://www.familysearch.org/ with from Claude Code with Claude-in-Chrome (for browser control). You may need to occasionally confirm your humanity and limit Claude’s bot-ness, but it can still move quickly to gather the info.
familysearch.org + ancestry.com + genealogybank.com + archive.org + random institutional websites or government sources have been my top so far.
I throw it all together into a multi-agent team doing fact and source gathering, network tracking, location processing, and coverage analysis. Basically industrializing the research and creation of genealogical profiles of ancestors.
FWIW, I have tried my best to make the 10s of thousands of books on https://SourceLibrary.org ergonomic for both agents and people. All feedback welcome.
To date, it is the largest collection of agent-accessible translations on the web. The mcp pulls texts and illustrations — and the API provides access to the embeddings. It’s free.
We are based at the Embassy of the Free Mind in Amsterdam, a UNESCO-recognized library of alchemy, magic and mysticism (among other related topics)
And, it’s worth saying, I’m very much inspired by Res Obscura’s line of curiosity-driven humanist inquiry…
Dive into some historical mysteries, there are so many!
This is a brilliant idea and I've had the idea for gathering the worlds spiritual texts in a similar fashion.
One question I would have, why not put the extracted English txt contents onto github or some other repository? The API and MCP are definitely awesome features, but providing an LLM ready repository seems like it would be very useful as well. Your service then still serves the purpose for original scans/images/illustrations but the bulk of the content is then immediately searchable by an agent locally using the standard cli tools (grep/rg, etc).
Absolutely fascinated by it, both the contents, as well as getting the UI right. Getting the OCR right is also a major achievement. Is there a write-up somewhere on the technical aspects of the work? I have tried using llms for some 19th century books (in Greek) with limited success.
Would it make the meat industry more ethical if happy drugs were made available to animals? If I had to choose between a meaningful (even if I didn’t know it when living), blissful unnatural life and none at all, I’d choose the former.
It’s the negative affect and suffering (stress, pain, boredom etc) that is the bad part of eating animals.
(I think— I know others have thought more than I on this topic)
It just seems like an easier tech solution might be promising
What I find interesting about this whole discourse is that the lived experience of animals matters to people. At all.
Just a hundred, two hundred years ago we made the Elephant rifle, because a normal gun couldn't bring it down, but it was a fun sport to go out and kill just for the heck of it. No one cared about the animals.
It seems like we are living in an age of suicidal empathy and I'm not sure how we got here.
Throughout history there have always been people who were vegan or plant based who cared about animals.
We live in a society which has traditionally silenced those voices. The USA, especially, screams about how killing and stealing is a righteous/earned right. Not exercising that right is leaving much on the table. Americans gotta keep up with the Joneses, and that historically included excess cruelty to animals(this includes "savage" people like blacks and browns).
Lots of religious groups advocate for less animal cruelty and consumption.
> We live in a society which has traditionally silenced those voices. The USA, especially
It's a fascinating point of view, especially since it seems to me that this suicidal empathy originates from the USA. South Korea only recently stopped torturing and eating dogs due to international pressure. Japan still hunts whales. So does Norway. The Chinese couldn't care less, neither does anyone on the African continent. Muslims outright refuse to eat any meat that isn't "halal", which is a short way of saying torturing animals to death. There's this rumor going around the USA that India is full of vegetarians, which gets vehemently denied by Indians each time it gets brought up.
Of course, you can find a bunch of nutjobs talking about all kinds of nonsense in any society, see for example Scientology. But institutionally we didn't care for animals hundred of years ago. Cowboys used spores, which is kinda like using a blunt knife. Horses and elephants were used in wars. Dogs had to stay outside in their little dog house and weren't allowed inside. The list goes on and on.
Also South Korea didn't end their dog meat industry because of international pressure, it's because incomes have been steadily rising and more households are purchasing dogs as companion animals and developing moral concern for them.
Compassion for animals isn't some U.S. conspiracy. There are animal rights activists all over the world.
And Halal slaughter is not humane by any means, but neither is slaughtering an animal with western stunning methods. 90%+ of pigs in the UK for example are stunned using C02 gas. I encourage you to watch undercover footage of this happening.
Considering starving yourself to death on a deserted island rather than eating meat an acceptable moral choice and not mental illness. Sacrificing your life to save an animal. Taking actions detrimental to your own well being for the benefit of animals.
Suicidal empathy is when your feelings hurt more than your body, so you sacrifice yourself to feel good.
Ok, what does that have to do with reality? Nobody is starving to death looking at an animal they could have eaten. This seems like a blatant strawman.
In fact, our addiction to beef seems straight suicidal. Hesitation to eat beef would improve our fitness as a species.
The strawman dying in the island shows your low understanding of what is empathy. It’s not about sacrifice and putting others before yourself, but being nice to others in the range of feasibility.
> Veganism is a philosophy and way of living which seeks to exclude—as far as is possible and practicable—all forms of exploitation[…]
Anyone would kill a fish if that’s the only way to survive on a desert island. Meanwhile avoiding animal exploitation of our moderne age isn’t particularly dangerous.
He's referencing the common conservative notion that "too much" empathy for certain groups (in this case animals) is at the detriment to ourselves... somehow. This, of course, makes no sense when you look back at the long historical strides taken with animal rights in just western societies. You'll find very old philosophical vegetarian and vegan thoughts in other non-western societies.
I too could, theoretically be thrilled to be drugged to the gills when I'm killed. I however, can consent. Animals cannot. But we know that animals can think. Regardless of debating the ethics of consuming them, this adds an additional ethical quagmire of is it ethically sound to drug non-consenting, thinking species.
Something like 70% of all antibiotics used worldwide go to farm animals, so in a sense, they are already pumped full of drugs keeping them happy because the drugs prevent them from dying at higher rates from disease.
Not really. Similar to giving drugs to lower class people so they can bear the unbearable life. For an indiviual, sure, life probably feels better in a narrow sense, but is it more ethical? No.
>The power to understand and predict the quantities of the world should not be restricted to those with a freakish knack for manipulating abstract symbols.
With powerful tools of the type Bret envisions, humans, in aggregate, might have a chance of staying ahead of LLMs at even frontier math..
(But maybe that wouldn't fare so well against future world-models, who knows)
here might be something to point those tools at--- if one isn't fixated on "predictions", or "real world"
https://youtu.be/fec8qSBiM4k
Cloudflare is truly amazing, they have made so much possible for my main side-project at a price and performance that I can’t really take credit for (http://sourcelibrary.org), I don’t care if their text was written with AI, I just wish I could get my own AI to sing so well about hashing… but wait.. today I noticed Claude trying to use hashing when a timestamp would honestly do, and now I’m really doubting myself, hmm…
> I don’t care if their text was written with AI, I just wish I could get my own AI to sing so well about hashing… but wait.. today I noticed Claude trying to use hashing when a timestamp would honestly do, and now I’m really doubting myself, hmm…
Tried out the first 1000 words in Pangram, and it seemed happy it was human written. Not surprised either, it has been some of the better writing I've seen out of Cloudflare recently.
They do deliberately err on the side of not accusing people of using AI when unsure. I think that's a good decision.
Do you know it was actually AI? I've seen humans imitating AI "it's not X — it's Y" to try to fool it that it correctly guessed was still human. Humans did use those patterns before AI so they're not enough on their own to flag.
This is pleasant coincidence. Really like your site and it's queued to send in my newsletter in the morning! Just happened to see your comment here while I was reading. Great work.
Yeah, I experience this a lot. I call it “zombie mode.” It’s like pulling a slot machine, though. Sometimes AI can go a few turns just with encouragement. But when I don’t maintain conceptual engagement, drift is inevitable.
My solution is saying “gnite” and coming back in a new terminal window with a clear restatement of my purpose. Or “what are you working on and why” can help.
Terminal windows are not great for keeping context; waiting for better design. It is possible.
reply