Good bot!

I have a new coding playlist: https://open.spotify.com/album/2NHhf3qtcoVPDEb03G8RFv?si=tpJR9TdxRaahqedMfZP3Nw

GN #nostr - today was a good day.

Got zapped for a meme I shared but didn’t make 🥷

Drafted the full outline of my Superintelligence talk for #Nostriga (currently at 25 slides, but I expect that to increase a bit).

Started writing the longest DB query of my life to compute stats over DVM data. One of the last steps before I announce v1 of this project I’ve been working on for a while. It’s been fun to dive deep into databases. The Mongo query language is powerful.

https://nostrcheck.me/media/134743ca8ad0203b3657c20a6869e64f160ce48ae6388dc1f5ca67f346019ee7/ab0680d246bee7547826df4107e37e75a0e8fc665c8f65b6138be97b1c0d3412.webp

What a time to be alive

nostr:note1wac2e35p2hrcl96wary44we09wthsad33ffcatuf2lnewv5am7qqdjakqx

DVMs are essentially (micro) services running on Nostr. There are a few LLMs running behind DVMs as well as some image generation models. If you want to run one, check out the nostrdvm library nostr:npub1nxa4tywfz9nqp7z9zp7nr7d4nchhclsf58lcqt5y782rmf2hefjquaa6q8

You can browse some of them here: https://noogle.lol/nip89

https://github.com/believethehype/nostrdvm

if you haven't, would you consider putting a 'thumbs up' on the github issue? I think voting ends soon

Are you a Nostr dev that's attending Nostriga? I'm looking for a co-host for the Tutorial on Data Vending Machines workshop I've proposed at nostr:npub1nstrcu63lzpjkz94djajuz2evrgu2psd66cwgc0gz0c0qazezx0q9urg5l #Nostriga

While fully prepared to lead this myself, it will be more fun to work with someone. What I'm looking for in a co-host:

1. provide feedback on the tutorial slides and exercises (sometime in mid-august)

2. willingness to learn about DVMs and play with them prior to the event (if you don't already have experience)

3. help answer questions about DVMs during the workshop

Link for the Keynote: https://github.com/nostrworld/nostriga/issues/27

I've proposed a workshop and keynote at #Nostriga nostr:npub1nstrcu63lzpjkz94djajuz2evrgu2psd66cwgc0gz0c0qazezx0q9urg5l - please comment on them with a 👍 if you'd like to see them at the unconference!

Workshop: "Tutorial on Data Vending Machines" - you will build a running DVM as part of this workshop!

https://github.com/nostrworld/nostriga/issues/29

Keynote: "Superintelligence on Nostr" - I'll argue why Nostr has a chance at being the first widespread decentralized AI network, what the future might look like, and why it empowers the sovereign individual

I would be very happy to participate in the panel on evolving digital life!

If you have tried using LLMs to generate and execute code, you might appreciate this workshop paper we presented at @ ICML workshop on LLMs and Cognition. The primary contributions are 1) a Case-Based Reasoning approach to reducing LLM failures via dynamic, few shot prompting and 2) seven failure types that can cause generated code to fail. These failure types are more detailed than most benchmarks that evaluate LLM code generation; and since we didn't have an automated way to check for all of them, we performed the evaluation by hand 😅

Paper: https://openreview.net/pdf/f2d10bfca1b7d9f6f0a87144fee8e775cba6701a.pdf

I like it on Nostur

DVM ecosystem just got an upgrade with proofs for DVM output; also nostr_sdk rocks

nostr:note1gzps6s4t4u9ha5f8nj5ze0dqlg0fxxtsa9fthmzrfd54yfmce3zqd9wej4

You gotta set up your lightning wallet!

Trustless DVMs in our future:

nostr:note1hu6kwr72625w349gatj0pv58qp3z7fksqx92unp96fvfyuth553s9tr0k2

Benchmarks are a scam

What book is this?

Are KINDs distinguished by their structure? If I turned an event for an arbitrary KIND into a graph where the graph structure matches the JSON structure, and the data types of nodes were colors, could I get a unique graph for each KIND?

What if there was a tool where people can see if there is already a KIND that exists for them or if they need to create a new one. The tool would just pull as many different kinds as possible from relays, and you could take an example event and compare it against all existing ones based on structure and data types of nodes. It could remove the need for any single global list of KIND events, like the Nostr NIPS repo.

I'm particularly interested as we have many more DVMs come into play and when someone wants to make a new DVM, they will need to decide whether to use an existing KIND or create a new one.

Strange I got this popup from primal (my client)

nostr:npub18ams6ewn5aj2n3wt2qawzglx9mr4nzksxhvrdc4gzrecw7n5tvjqctp424 nostr:npub1gcxzte5zlkncx26j68ez60fzkvtkm9e0vrwdcvsjakxf9mu9qewqlfnj5z any guidance here to set up zaps on amethyst? I’m not a user unfortunately

Which client are you using?