Avatar
ABVStudio
a452c27fe801c18fe10b738fcb86141e27bdedd254055faaf40696e72fc1cc0a

GN nostr.

Tomorrow - we vibe!

There are sharp corners around "bleeding edge" tech.

Hopefully you only lose a "few" sats - nothing yuge.

Don't believe the "AI destroys critical thinking" memes floating around.

Critical thinking is a muscle you can always decide to use - no matter if you're browsing online coding tutorials, StackOverflow forums... or just asking an AI model the best way to do something.

Trial and error, experimentation and effort... there's no better lesson than just building something.

nostr:nevent1qvzqqqqqqypzq5xeflpdskqvdq4swxj59793uvdzqzc9pzatjk3nhmcg2h0js8trqy08wumn8ghj7mn0wd68yttsw43zuam9d3kx7unyv4ezumn9wshsz9nhwden5te0v4jx2m3wdehhxarj9ekxzmny9uq3vamnwvaz7tmgd9ehgtnwdaehgu3wd3skuep0qqsqaa8axllvr403ksuxjg8qpw63hpvse2yqzscxf7kjwcnxgec5lgcp5hwhj

BREAKING NEWS: People pay attention to catchy headlines but often fail to critically read article contents!

Can AI help with this human frailty!? Zap to find out...

I like to re-try vibe coding tools every few months as some of them are rapidly improving. I've been most impressed with Cline, as well.

BUT - my personal goal is to use open-source models and it wasn't until Qwen3-Coder that it FINALLY worked well-enough for me.

Just wait 6 more months...

Seriously? Not sure this is authentic... but it wouldn't be the first time chat logs have been leaked or "turned over" to authorities.

THIS IS WHY WE USE PRIVATE AI, PEOPLE!

Protect your privacy. Use nostr:nprofile1qyxhwumn8ghj7mn0wvhxcmmvqydhwumn8ghj7mn0wd68ytnzd96xxmmfdecxcetzwvhxgegqyz9lv2dn65v6p79g8yqn0fz9cr4j7hetf28dwy23m6ycq50gqph3xc9yvfs.

nostr:nevent1qvzqqqqqqypzqcufhejfreakj05lx68vaz8u69zlqlqx35kphwhyy3aekhh588fjqyt8wumn8ghj7etyv4hzumn0wd68ytnvv9hxgtcpzemhxue69uhks6tnwshxummnw3ezumrpdejz7qpq6fcajcrleluvccmsg4ysyp4sqh7s85xpqj0n5uwd5su744nvegns82kdwt

#asknostr how do we feel about coding-assistants?

Has anyone used VS Code's Cline extension? It seems to have a very active Github community and I've noticed it get a lot better over the last few months.

GPT-OSS is a good open-source model and runs very fast for being 120B parameters.

But it was clearly created from synthetic data, hallucinates a lot, and was designed NOT to take business away from OpenAI. For example, it's not as good as coding / agentic workflows as open-source Chinese models like Qwen3-coder. For that they sell GPT-5 (which is best-in-class IMO)

It is good at plenty of tasks though, so it's worth downloading and having around if you need it.

Or, try nostr:nprofile1qyxhwumn8ghj7mn0wvhxcmmvqydhwumn8ghj7mn0wd68ytnzd96xxmmfdecxcetzwvhxgegqyz9lv2dn65v6p79g8yqn0fz9cr4j7hetf28dwy23m6ycq50gqph3xc9yvfs and pay a few sats for an anonymous chat.

IT WORKS! nostr:nprofile1qyt8wumn8ghj7etyv4hzumn0wd68ytnvv9hxgtcpzemhxue69uhks6tnwshxummnw3ezumrpdejz7qpq2rv5lskctqxxs2c8rf2zlzc7xx3qpvzs3w4etgemauy9thegr43sugh36r is building magical internet technology.

"Qwen3 Coder 30B A3B" is one of the largest LLMs I run locally at 36GB! But, it's faster than models half its size!

The secret is the "A3B" in the name, which means only 3 of the 30 billion parameters are "active" per token. This allows it to be SMARTER than smaller models, while being FASTER at the same time. Plug it into VS Code with Cline's agentic coding extension and get 👏 back 👏 to 👏 vibin'! #vibecoding

Isn't there a way to get a free lightning address with cashu? nostr:nprofile1qyt8wumn8ghj7etyv4hzumn0wd68ytnvv9hxgtcpzemhxue69uhks6tnwshxummnw3ezumrpdejz7qpq2rv5lskctqxxs2c8rf2zlzc7xx3qpvzs3w4etgemauy9thegr43sugh36r

your_npub@cashu.me? Is that right? #asknostr

Replying to Avatar Thefux

otrta 0.1.2

We're thrilled to announce some powerful new features that enhance your AI experience:

* Nostr Marketplace Discovery: Easily discover providers with NIP-91 support!

https://imgproxy.coracle.social/x/s:640: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

* Model Comparison: Find the best model prices with our new comparison view!

https://imgproxy.coracle.social/x/s:640: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

Future Plans:

We're already working on more innovations, including:

* Automatic provider switching for the best model prices!

* setup api key budget limit

Stay tuned for more updates!

I'd love to get started as an inference provider. I've read through the docs but still have a few questions. Do you have a discord or anything for providers to get together and help each other?

Study AI, or fall behind.

nostr:nprofile1qyxhwumn8ghj7mn0wvhxcmmvqydhwumn8ghj7mn0wd68ytnzd96xxmmfdecxcetzwvhxgegqyz9lv2dn65v6p79g8yqn0fz9cr4j7hetf28dwy23m6ycq50gqph3xc9yvfs how do I become a provider? I reviewed the docs and have a few questions. Do I have to run my own mint?