I use sparkey / hammerspace for caching static data (tried rocksdb but hammerspace was faster) for many years.
It helps me have a 20ms on a 100r/s on a ruby on rails app (ruunning on a ryzen 5950X). I keep seeing people brag about 100ms on applications and maybe I’m old school or haven’t seen enough, but 100ms breaks personal SLO. will trigger a 5-alarm alert.
Also use redis a lot. But when possible, I use hammerspace/sparkey instead of it.
I guess the people who are not aware of this effect might make a lot of decisions in life and a confident AI agent will be like a high-tech con-artist.
As a child, I would read the horoscope of the day with the wrong sign for mother and her female friends and they always thought it was talking about them and I never had the courage to tell them I switched as a joke. I keep imagining a fine tuned GPT for insights from the "mystic realm".
I don’t think it’s the ADHD. I have it but I’m very conservative on the stack. And I know many developers who don’t have ADHD, some newbie and some who code longer than 20 years and are going after the latest shiny thing.
I think it’s more of what people assume it’s a status symbol among their peers. I noticed for example, in church, that some people think the more boring is more saint and don’t like more a church with a more contemporary dynamic approach and I think the same effect applies in the software development world.
Maybe should be called Prompt Science or Prompt Discovery or even Prompt Craft.
I have a 40 million BERT-embedding spotify-annoy index that I keep experimenting with to make a better query vector.
One way that I’m doing is getting only the token vectors with the highest sum of the whole vector and averaging the top vectors to use as the query vector.
Another way is zeroing many dimensions randomly on the query vector to introduce diversity.
But after experimenting with “prompt engineering” I found out that prefixing the sentences for the query vectors with “prompts” yield very interesting results.
But I don’t see much engineering. It’s more trial, feedback and trying again. Maybe even Prompt Art. Just like on chatGPT.
It helps me have a 20ms on a 100r/s on a ruby on rails app (ruunning on a ryzen 5950X). I keep seeing people brag about 100ms on applications and maybe I’m old school or haven’t seen enough, but 100ms breaks personal SLO. will trigger a 5-alarm alert. Also use redis a lot. But when possible, I use hammerspace/sparkey instead of it.