Load previous page…
reading about chatgpt seo as more people are saying they discovered the service through it 
#thecompaniesapi
renew cloudflare enterprise this year for 
#crisp, but tell them that we'll reduce reliance on them in the future cause they are constantly raising prices and now we pay 7k USD a month for a few add-ons, which more than we pay for all our server infrastructures at DigitalOcean, combined. CF is great but as soon as you go ENT it becomes an extractive business, akin to a drug dealer selling you addictive shit and then you're hooked and they can raise prices whenever they want and you still have to pay otherwise you're fucked
Time-non-critical agents are super slow because you use flex mode in OpenAI to save costs.
Now with gpt-5 they became even slower (and cheaper, so it's a good thing!).
So you *need* to parallelize your agents.
This is what I've been doing last night. My library 
#monoflux's flatMap method on a Flux (a Flux is an asyncronous array) can now handle () => Flux callbacks.
It is now my number 1 engine to run *tons* of agents in parallel.
The Kora assistant finally has a sensible memory and performed the first two urgent tasks for me that I really didn't want to perform, keeping in mind many details about the projects these tasks were related to.
