sidnb13

I don't think vector databases are intended to be secure, encrypted forms of data storage in the first place.

+1, immensely satisfying read for any aviation nut

Cool to see that this worked well for someone. Super hard to force the key insight in a problem to magically appear given more time sunk into it. Big weakness of mine honestly, and requires a lot of self-awareness to pull myself out of a problem-solving rut. I like the idea of hacking sleep - do you find yourself priming your mind with the problem before nodding off? Curious how a bedtime wind-down routine factors into how effective this is.

Wow, sorry to hear that. Came across his blog in 2021 and was instantly hooked. RIP

Very cool. I used to dream of this stuff when I was younger. Reminds me of Atlantik Solar: https://www.atlantiksolar.ethz.ch/. Hasn't been updated in a while, but focused more on low-altitude autonomous survey missions.

Ah that would make sense. Similar to vLLM which does dynamic packing.

I would assume the datacenter and infra needed would also contribute a sizeable chunk to the costs when you consider upkeep to run it 24/7

> I also believe that within say 1-3 years there will be a different type of training approach that does not require such large datasets or manual human feedback.

I guess if we ignore pretraining, don't sample-efficient fine-tuning on carefully curated instruction datasets sort of achieve this? LIMA and OpenOrca show some really promising results to date.

Yep, batching is a feature I really wish the OpenAI API had. That and the ability to intelligently cache frequently used prompts. Much easier to achieve this with a hosted OS model, so I guess it's a speed + customizability/cost tradeoff for the time being.

maybe worth looking into: https://news.ycombinator.com/item?id=36750083

Maybe worth looking into: https://news.ycombinator.com/item?id=36750083