make community posts asking for advice on speeding up generation time #ai

investigate why #nomads filtering sometimes takes 5 seconds when it should be instant and fast

playing around with speeding up tools to run faster. I think anything over 200ms is going to make me rethink any/all usage

model all steps of next project ... let’s see if this approach saves time

my impression with o1 so far: it requires more "thinking" from the human as well. To get the best result, I find myself writing a well thought through "letter" to the model vs. rapid fire "sms" to a simpler model without the reasoning capabilities. And yes, I create that "letter" with a simpler model during the initial "exploration" phase.

read about ways to speed up initial load #fotoloods

Fix intermittent slow stock insights responses #wallstrank

speed up #remoteok from 10 second load to 600ms by removing the suggested remote worker profiles at bottom of profile because it takes too much time to query now with 1 million profiles

Work on speed improvements for #booklet

speed up load times #instaaa

add speed profiling to #nomads filter API to see if/where bottlenecks are

Simplifying complex processes for better usability #mangobeds

Simplifying complex processes for better usability #mangobeds

Simplifying complex processes for better usability #mapmelon

figure out bottleneck with a function that runs everytime someone visits the lessons dashboard, decreasing server loadtime by 58% #pe

Asking questions to myself about actions I am doing and correcting them as I go

bb: figure out ways to speed up loading of chat. seems to be loading twice?

#thecompaniesapi improve the dx of our AI flows so we have faster feedback loop in development, noticed it was making me lazy that i had to wait for app rebuild to rerun everything

doing the simplest thing and than the next simplest thing. experimenting whether this gets momentum going #ing #ekh

speed up #scrapebook