Some interesting DVMs are popping up. Found on

Nostr decentralized search and other stuff

Are there any LLM projects for entire code bases? Feels like I should be able to train an LLM on Damus source code to get suggestions on how to add translations into Nostur…

@PABLOF7z @StarBuilder I updated NIP 90.md PR so that customer feedback is a kind:7, FYI

GitHub

Update 89.md and 90.md with Customer Feedback Data by dtdannen · Pull Request #985 · nostr-protocol/nips

This adds an additional protocol flow step to Nip-90 where a Customer can provide feedback back to the service provider.

Could we make NIP-25 Reactions include arbitrary strings like “this worked but took too long” or numbers like “96” ? Terrible idea? Currently the spec says it’s for emoji or ‘+’ or ‘-‘ I want to expand it so we can give DVMs the reactions they deserve (with flexibility on the amount of detail)

GitHub

nips/25.md at 8331354947f2d577e13eb5da4a56133071cb1019 · nostr-protocol/nips

Nostr Implementation Possibilities. Contribute to nostr-protocol/nips development by creating an account on GitHub.

Oh boy I could really use an LLM fine-tuned on the NIPS docs right now.

DVMs will help clients and relays be lighter, by offloading computation. Algorithms for sorting your feed could be done via DVMs.

If you’re interested in AI, Rao is one of the best perspectives to have. Cuts directly through the hype and his lab has lots of papers to back up his claims. Not on Nostr yet, for now Twitter and LinkedIn seem to be where he posts

Doesn't the fact that LLMs can "write code" prove that they can also reason and plan? (Hint: Nope..) (Part 2/2) Continued from Part 1 https://lnkd.in/gz5Wr7da In contrast, though, the code data for… | Subbarao Kambhampati | 13 comments

Doesn

I have proposed an update to NIP-90 for a customer feedback event:

GitHub

Update 89.md and 90.md with Customer Feedback Data by dtdannen · Pull Request #985 · nostr-protocol/nips

This adds an additional protocol flow step to Nip-90 where a Customer can provide feedback back to the service provider.

and created an issue on vendata.io to add a user interface element so a user can send a `customer-feedback` after the DVM has finished.

GitHub

Add human feedback response to output · Issue #5 · pablof7z/vendata.io

When the result comes back from the DVM, allow the user to like or dislike, use a reaction emoji, and/or add text describing their feedback. This f...

@PABLOF7z @StarBuilder thoughts?

If a client chooses to make a new feature via DVM, then other clients could adopt the feature quickly. Consider recommending new people to follow on Nostr. Each client could implement their own version, or instead one person could make a DVM that other clients hit to get the data. DVMs may cost money but paying per each request to the DVM probably doesn’t always make sense. “Salaried” DVMs might be a solution. Client subscription fees could cover DVM fees. Free clients wouldn’t have the paid DVM features. Network effects would be insane here!

It’s interesting how actions are chosen across different LLM agents. Judging from the description on OpenAI's website, the decision of which function (aka tool) to use is decided by the model (i.e. GPT4) based on the user’s incoming message and chat (thread) history. “In this example, we define a single function get_current_weather. The model calls the function multiple times, and after sending the function response back to the model, we let it decide the next step. It responded with a user-facing message which was telling the user the temperature in San Francisco, Tokyo, and Paris. Depending on the query, it may choose to call a function again. If you want to force the model to call a specific function you can do so by setting tool_choice with a specific function name. You can also force the model to generate a user-facing message by setting tool_choice: "none". Note that the default behavior (tool_choice: "auto") is for the model to decide on its own whether to call a function and if so which function to call.” See https://platform.openai.com/docs/guides/function-calling

Happy new year #Nostr ! 2023 was incredible, can’t wait for 2024!

Has anyone made a bot that pings you when someone has posted to a community you are moderating, so you can immediately review it? I started a community about ai-papers and missed a post from someone a few weeks ago. I didn’t get a notification in Nostur or Damus. If this doesn’t exist yet, I may try my hand at setting it up.

Maybe AGI will be just one big NN architecture in the end…

Supersizing Transformers: Beyond RAG with Extended minds for LLMs - Normal Computing

In this blog we discuss how the transformer architecture naturally extends over external memories, and share empirical results which leverage this ...

I’m still curious what the limitations of the memory cache is here and whether you can keep adding to it without having to retrain it if the cache changes.

We now have a tentative #NostrNovember meetup scheduled for November 15th at 7pm in Leesburg, VA. If you’re interested and can’t make this time, please let me know!

Meetup

NOVA Nostr Meetup Group - Meet and Greet, 15 Nov 2023, 07:00 PM, Wed, Nov 15, 2023, 7:00 PM | Meetup

Let's chat about everything Nostr! I'm hosting a low-key event to get to know you all a little better. During our Meet and Greet, we'll discuss thi...

@Derek Ross @average_bitcoiner @szarka