Dustin Dannenhauer's avatar
Dustin Dannenhauer
dustind@dtdannen.github.io
npub1mgvw...pdjc
DVM maximalist Building DVMDash - a monitoring and debugging tool for DVMs https://dvmdash.live Live DVM Stats here: https://stats.dvmdash.live Hacking on ezdvm - a python library for making DVMs https://github.com/dtdannen/ezdvm
Dustin Dannenhauer's avatar
Dustin 1 year ago
I really want a feed of funny nostr notes, I’d possibly even pay for it if it took human(s) to curate it
Dustin Dannenhauer's avatar
Dustin 1 year ago
I don’t know who needs to hear this, but be careful with serverless database hosting solutions. I may have accidentally racked up $640 in db bills in 4 days…😅 Luckily the folks at mongo are wonderful and gave it all back to me in credits
Dustin Dannenhauer's avatar
Dustin 1 year ago
Is nostr.band not loading search results for anyone else?
Dustin Dannenhauer's avatar
Dustin 1 year ago
Super excited to give my talk "Superintelligence on Nostr" at @Nostriga ! Here's a teaser slide: image
Dustin Dannenhauer's avatar
Dustin 1 year ago
@Don't Believe The Vibe 🌱🍋🍊 nostrdvm lets you specify 'params', but is this defined anywhere in nip-89? @PABLOF7z I know vendata.io will show fields based on the 'params' of the nip-89 for a dvm? Did you just decide to do this or is it based on a NIP somewhere?
Dustin Dannenhauer's avatar
Dustin 1 year ago
Is there any existing mint that offers sub 1 sat denominations? Looking to get my hands on some .01 or .001 sat ecash for testing purposes
Dustin Dannenhauer's avatar
Dustin 1 year ago
haha just another day on Nostr, reminds me of the early ecash days, keep building 💪 image
Dustin Dannenhauer's avatar
Dustin 1 year ago
Turns out writing a fast, scalable data pipeline can be a little tricky... GN
Dustin Dannenhauer's avatar
Dustin 1 year ago
Did ecash appear on Nostr before Zaps? I'd love to know when the first ecash payment was sent on Nostr and when the first Zap was sent on Nostr. I'm working on a timeline that involves some of Nostr's history. Seems like December 2022 to February 2023 is the time range for both? @calle @jb55
Dustin Dannenhauer's avatar
Dustin 1 year ago
what's your favorite relay to use for quick testing?
Dustin Dannenhauer's avatar
Dustin 1 year ago
It would be cool if we could visualize github NIPs as conversations, so all the pull requests and comments could be ordered chronologically, and it would be easy for someone to skim a nip from past to present and see everything. The problem with the history tab for a single NIP is that it doesn't show the content of the commits or any comments from PRs, etc. I guess that doesn't solve any conflicts between proposals / suggestions though...
Dustin Dannenhauer's avatar
Dustin 1 year ago
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 @Nostriga #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
Dustin Dannenhauer's avatar
Dustin 1 year ago
I've proposed a workshop and keynote at #Nostriga @Nostriga - 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! 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
Dustin Dannenhauer's avatar
Dustin 1 year ago
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 image