Load previous page…
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.
Doing a comprehensive data flow review for
#desci at the State Treasury Buildings in Perth, WA.
Post about commission calculator plugin (commissioncalculator.carrd.co) on personal Twitter/X account - x.com/jasonleowsg/status/1968…
#pluginsforcarrd #marketing365
Need to add to every AI interaction: Don't give me options unless I ask for them. I'm so tired of having to parse through 3 alternatives that aren't as good as the preferred alternative, which is almost always the right choice, but is usually the second or third alternative. Just give me the best, and if that isn't right I'll ask you to try again. #llm #ai #vibecoding