All the excess votes were casted one way; what are the odds 🙃

Meetup Bitcoin Paris🇫🇷 ! 🥂 Une soirée mémorable avec la possibilité de payer nos bières en Lightning Network ! 🌩️ De belles rencontres, des échanges passionnants, et l'énergie de cette communauté en plein essor. Merci à tous les participants pour ce moment enrichissant ! Prêt à renouveler l'expérience. 🔥 #Bitcoin #LightningNetwork #MeetupParis" 🇬🇧 English version: "What an amazing Bitcoin meetup in Paris! 🥂 An unforgettable night with the chance to pay for our beers using the Lightning Network! 🌩️ Great people, exciting discussions, and the incredible energy of a growing community. Thank you to everyone who came out for this inspiring event! Ready to do it again. 🔥 #Bitcoin #LightningNetwork #MeetupParis https://www.sofsbar.fr/ https://www.meetup.com/fr-FR/bitcoin-paris/

WHEN #BITCOIN PUMPS nostr:note1ukr4frcfnafg5dylwws7sdmrhrxjygwn8la2v32k0l0kda0taynqxzq8kw

WHEN #BITCOIN PUMPS nostr:note1ukr4frcfnafg5dylwws7sdmrhrxjygwn8la2v32k0l0kda0taynqxzq8kw

😂

Almost as if under a gold standard and no central bank people were able to build beautiful things.

Did you know

NOCOINERS IN DISBELIEF AS THEY WATCH THE RISE OF #BITCOIN

NOCOINERS IN DISBELIEF AS THEY WATCH THE RISE OF #BITCOIN

มันคืออนาคตที่แท้ทรู #siamstr #bitcoin #rightshift #นครสวรรค์ #แอดิเลด #Adelaide #zatoichi

มันคืออนาคตที่แท้ทรู #siamstr #bitcoin #rightshift #นครสวรรค์ #แอดิเลด #Adelaide #zatoichi

Crazy productive today. I should stay up for 28 hours more often. 💥

It’s happening in Suriname 🇸🇷 #bitcoin #NOSTR #bbq 🔥

It’s happening in Suriname 🇸🇷 #bitcoin #NOSTR #bbq 🔥

New emissions cap is going to double that candle when our beaver buck is worth 50 cents!

Basically always. Only a few of us care enough to do it.

Thanks Beth! We are having a Time!!

{"id":"c1734165a5a7c1f21207c00a32fee9c6b9b9e5b56701276f254544499ff6dc9c","pubkey":"1989034e56b8f606c724f45a12ce84a11841621aaf7182a1f6564380b9c4276b","created_at":1730926695,"kind":1,"tags":[["a","30311:cf45a6ba1363ad7ed213a078e710d24115ae721c9b47bd1ebf4458eaefb4c2a5:f5108cfd-02fe-4706-bcb1-d54b8c91b535","wss://nostr.wine/","mention"]],"content":"SUPPORT NOSTR STREAMERS! GET IN HERE AND ZAP!\n\nnostr:npub1cj8znuztfqkvq89pl8hceph0svvvqk0qay6nydgk9uyq7fhpfsgsqwrz4u stream on zap.stream! https://zap.stream/naddr1qqjxvdf3xquxxeny95cryen9956rwvpk943xxc3394jr2drz8p3njvtzx5en2qg3waehxw309ahx7um5wgh8w6twv5hsygx0gknt5ymr44ldyyaq0rn3p5jpzkh8y8ymg773a06ytr4wldxz55psgqqqwensl5lt0g","sig":"7935b3cd89732b2b5f987cd7c04187a4c0e16ae3f70ca10c12c20d0b1f1376aa4ab23a72043399faf05a4402f0a69f090024972515605d24ec016f2d1ad05f01"}

{"id":"399ef34695cf1058cc176b88a22aa40d812987622766952f2567d6a0ea2bc376","created_at":1730926470,"content":"nostr:npub1rtlqca8r6auyaw5n5h3l5422dm4sry5dzfee4696fqe8s6qgudks7djtfs x nostr:npub1hk0tv47ztd8kekngsuwwycje68umccjzqjr7xgjfqkm8ffcs53dqvv20pf x nostr:npub10qrssqjsydd38j8mv7h27dq0ynpns3djgu88mhr7cr2qcqrgyezspkxqj8 nostr:note1r0yryfk9gwdfhyq639ml5f605u4yg42jjnqh6uuz5l5xqxsax23suhragj","tags":[["p","c48e29f04b482cc01ca1f9ef8c86ef8318c059e0e9353235162f080f26e14c11"],["p","1afe0c74e3d7784eba93a5e3fa554a6eeb01928d12739ae8ba4832786808e36d"],["p","bd9eb657c25b4f6cda68871ce26259d1f9bc62420487e3224905b674a710a45a"],["p","7807080250235b13c8fb67aeaf340f24c33845b2470e7ddc7ec0d40c00682645"]],"pubkey":"c48e29f04b482cc01ca1f9ef8c86ef8318c059e0e9353235162f080f26e14c11","kind":1,"sig":"8a2c9d794dd8afe042a19f0a86ddd34e9ab4e3719d76eb2722e74f8dde90305293c90c45d2794c771d204d9578c528f2932d4b902b809c3c41b3bf25ff095f3a"}

Fuuuuck! I really don’t have enough#Bitcoin!

Fuuuuck! I really don’t have enough#Bitcoin!

What I've done in the past was write functions/tools [1] that can interface with the data and write a system prompt that guides the LLM in using it. This would be an agent setup where you have multiple back-and-forth requests to the LLM for each user prompt. In my case I had parquet files on my network and wrote functions that used DuckDB to query them. Then I wrote documentation for the functions and passed them along to the LLM and let it figure out what args to pass. You can also add high-level instructions and advice. LLMs are also decent at using Pandas and Numpy and Matplotlib so consider giving access to those tools as well. I've found that it can be useful to create agents that specialize in different tasks too. For example, an agent that can formulate the queries and fetch the data (possibly storing it somewhere and returning a reference to that location) and then another that specializes in modeling. 1. https://ollama.com/blog/tool-support

Ah, the cracks in the matrix..

let's go

Just imagine combining that cost with Kamala's campaign! At least Elon will get a kick back.