10
[-] zinderic@programming.dev 5 points 3 months ago

Almost ready for it's prime time I think. We just need a bit more on the UI/mobile app friendliness to make it shine for all.

27

I love playing with LLMs locally at home. The cost of running hobby projects against paid services like OpenAI is too high for me so in this article you can find out how I work around that to keep my LLM infra deployed locally at home and still use it anywhere I like.

[-] zinderic@programming.dev 7 points 3 months ago

To me this looks like a Doctor Who episode. We have the Dalec and the Tardis in the scene 😂

275
Go vs Rust learning (programming.dev)
[-] zinderic@programming.dev 7 points 4 months ago

Old bands such as Joy Division are amazing and most new music doesn't even get close to that.

[-] zinderic@programming.dev 25 points 4 months ago

Okay, one thing for me to do then..

rad seed rad:z3SNcAzHydhWtfaFTiq9S643GQjYU

Done! :)

[-] zinderic@programming.dev 13 points 4 months ago

I think this model can reach Null Island from anywhere, doesn't have to be Europe. Can't wait to see what else it's capable of. But kind of hoping it won't murder me in my sleep.

171
[-] zinderic@programming.dev 5 points 5 months ago

I think that the idea here is to get user attention towards more "linked" videos rather than things they normally look for. Cheap trick.

[-] zinderic@programming.dev 6 points 5 months ago

There will always be people in both cases thinking they are entitled to the work of others. There will be nice people who do nice by others too, rarely but that happens. We live in a wonderful world and not being an a..hole about things makes it better.

[-] zinderic@programming.dev 7 points 5 months ago

Give https://github.com/louislam/uptime-kuma a try. I'm planning to do the same for similar use case. Sensu (sensu.io) is a more sophisticated option but it requires more infrastructure and there is a bit of a learning curve with it.

30

Seems interesting. It covers the basics and it's easier to setup than Sensu that I use today.

[-] zinderic@programming.dev 7 points 5 months ago

XML or JSON - does it matter? Turtle is a turtle, same principals apply, just different structure. What happened to server side rendering? Oh, we do that with fancy frameworks and ton of JS now. All good.

[-] zinderic@programming.dev 7 points 6 months ago

That would be amazing. But it won't happen any time soon if ever.. I mean - just think about all that investment in GPU compute and the need to realize good profit margins. Until there are laws and legislation that requires AI companies to open their data pipelines and make public all details about the data sources I don't think much would happen. They'll just keep feeding any data they get their hands on and nothing can stop that today.

[-] zinderic@programming.dev 33 points 6 months ago

It's almost impossible to audit what data got into an AI model. Until this is true companies could scrape and use whatever they like and no one would be the wiser to what data got used or misused in the process. That makes it hard to make such companies accountable to what and how they are using.

[-] zinderic@programming.dev 13 points 6 months ago* (last edited 6 months ago)

Right. Why should someone write 10 lines of yaml when they can program 20 lines of Go? Or python. Or assembly for a risc cpu because it just feels so friendly with that nice instruction set.

view more: next ›

zinderic

joined 6 months ago