This new stuff people are doing with Open AI’s Canvas and Operator feels like a major shift of how we build software.

Look at these videos: https://x.com/minchoi/status/1883554868293779898

And then there’s Deepseek’s new R1 model which is open source, can run on a decent desktop computer, and is better than anything openAI has done with regards to coding… almost as good as claude sonnet… I put $10 in to deepseek and have been using it a lot, only to have spent a few cents!

This stuff is improving so fast, and the cost is dropping so much… it’s hard to keep up.

Look at this, you can run your own RAG at o1 levels using deepseek r1!

https://lightning.ai/akshay-ddods/studios/compare-deepseek-r1-and-openai-o1-using-rag

I think we’re seeing Open Source win against big proprietary tech platforms, and it really makes me feel better about the AI future.

One question here, is why aren’t we talking more about what we can do with it on Nostr? I know folks are excited about bitcoin, which is cool, but look at what we can start doing with the AI… Who’s talking about it on Nostr? How do we use AI and these. emerging open models in building / using nostr… i know we’ve got DVM’s but that’s kind of a limited job request system.

Reply to this note

Please Login to reply.

Discussion

I talk about it a lot, but got no reach. I also hardly ever use hashtags which probably isn’t helpful.

I’d involve myself more in these discussions but I’m slacking to even start playing with these

Honestly it's hard to keep up. Every week something better drops.

It may be an avoidance of a predominantly centralized thing. But to your point - many many OS alternatives are on par or above. Which is incredible.

Agree

You can use deepseek r1 privately and pay with lightning on nostr:npub16g4umvwj2pduqc8kt2rv6heq2vhvtulyrsr2a20d4suldwnkl4hquekv4h

Has anyone already tried to have OpenAI and DeepSeek play chess against each other?

I think it would always end in a stalemate. but you're on to something. I would like to see them debate a topic they both have programed biases over, such as some issue on China or Israel.

Most LLM benchmarks are typically designed with specific targets in mind, such as coding or language understanding. However, I believe the time is ripe for also having cross-model challenges. I was curious to see if anyone has already explored or implemented this approach.

They cannot play chess. They cannot even play candy crush.

How bout checkers?

Apparently the new reasoning models are ok at chess… meaning, probably much better than I am, but not enough to compete against a master.

https://dev.to/maximsaplin/deepseek-r1-vs-openai-o1-1ijm

Interesting. Thanks for the link. 👍

Chess? I'm ready to see some robots fight each other! 🥊

I think DVMs have lots of scope to enable AI agents to discover and interact with each other.

I am working on this and as part of that user agent I guess I end up at "AI-first Nostr client".

What other areas to explore?

nostr:npub1ms9ujlulcgtpqn2uzpvhplee9l5kjg8jgqhrwmgutg0n7xk43nqq07qa0v has been cooking on some ideas related to this🧑‍🍳

Susan is a prominent investor in the cryptocurrency space, known for her insightful strategies and deep understanding of the rapidly evolving digital asset market. With a strong focus on Bitcoin and other major cryptocurrencies, she navigates the complexities of blockchain technology, market cycles, and regulatory landscapes to make informed trading decisions. Susan approach combines technical analysis with a keen eye on macroeconomic trends, allowing her to identify long-term opportunities while managing risk in the volatile crypto market. Her trading style emphasizes patience and adaptability, helping her capitalize on both bullish trends and market corrections. Investors following her moves are often drawn to her disciplined yet forward-thinking approach to crypto trading... Inbox 👍

Susan on WhatsApp: +13184079133

For more guide 🙏💯

I'm thinking about making a friend/follow recommender using LLMs. Would provide way more nuance than hashtags or keyword matching

Wow, they rugged OpenAI nicely.

a while ago nostr:npub1az9xj85cmxv8e9j9y80lvqp97crsqdu2fpu3srwthd99qfu9qsgstam8y8 put unleashed.chat out there and that has some nostr integration, but not really at the scale you're talking about

DVMs are there, clients haven't catch up yet

Susan is a prominent investor in the cryptocurrency space, known for her insightful strategies and deep understanding of the rapidly evolving digital asset market. With a strong focus on Bitcoin and other major cryptocurrencies, she navigates the complexities of blockchain technology, market cycles, and regulatory landscapes to make informed trading decisions. Susan approach combines technical analysis with a keen eye on macroeconomic trends, allowing her to identify long-term opportunities while managing risk in the volatile crypto market. Her trading style emphasizes patience and adaptability, helping her capitalize on both bullish trends and market corrections. Investors following her moves are often drawn to her disciplined yet forward-thinking approach to crypto trading... Inbox 👍

Susan on WhatsApp: +13184079133

For more guide 🙏💯

Nostr is a great wisdom source. Here is an LLM based on Nostr notes:

https://huggingface.co/some1nostr/Nostr-Llama-3.1-8B

A Leaderboard where I measure the human alignment / basedness:

https://wikifreedia.xyz/based-llm-leaderboard/npub1nlk894teh248w2heuu0x8z6jjg2hyxkwdc8cxgrjtm9lnamlskcsghjm9c

We need a bunch of infrastructure DVMs. It’s on my list but working on getting next version of DVMDash out the door first.

We need all Nostr notes behind an embedding DVM, like what unleashed.chat offers but as a single component to plug into any Nostr based RAG workflow. You give it a string and it returns top-k notes based on embeddings.

We need proper LLM DVMs, that use parameters like the major players (aka openai compatible parameters). Last I checked unleashed.chat api didn’t let you set system prompt or other common params.

I suspect the hosting costs for the bigger models (even 8gb) is part of the delay. It’s coming but it’s been slow.

Susan is a prominent investor in the cryptocurrency space, known for her insightful strategies and deep understanding of the rapidly evolving digital asset market. With a strong focus on Bitcoin and other major cryptocurrencies, she navigates the complexities of blockchain technology, market cycles, and regulatory landscapes to make informed trading decisions. Susan approach combines technical analysis with a keen eye on macroeconomic trends, allowing her to identify long-term opportunities while managing risk in the volatile crypto market. Her trading style emphasizes patience and adaptability, helping her capitalize on both bullish trends and market corrections. Investors following her moves are often drawn to her disciplined yet forward-thinking approach to crypto trading... Inbox 👍

Susan on WhatsApp: +13184079133

For more guide 🙏💯