Aghits
573 posts


OpenUsage v0.6.24 is out
xAI/Grok Build subscription usage is now available!
also a bunch of bug fixes for Claude and other plugins, plus performance optimizations thanks to recent ccusage updates of @ryoppippi
going forward we're going to aggressively close/decline new features and focus on stability more than anything else
thanks to everyone who's contributed :)

English
Aghits retweetledi

Gemini 3.5 Flash (Medium) is 🥇 on AutomationBench!
Also note that medium thinking performs better than high, which matches our own evals. medium is the new default API setting and we recommend it for most tasks. more info are on the model guide:
Bryan Helmig 🍻@bryanhelmig
gemini 3.5 flash (med) is the new leader 14.5% on zapier's automation bench and roughly 7x (!!!) cheaper than gpt 5.5 (xhigh) 12.9% 3.5 flash is the most persistent model we've seen yet. thats why high reasoning scores lower than med -- it maxes out our tool call limit. we may revisit this for automation bench v2. zapier.com/benchmarks
English
Aghits retweetledi
Aghits retweetledi
Aghits retweetledi

Here's the formula:
1. If you don't know what works, run a lot of experiments
2. When something is working, double down
3. Repeat until it stops working
Repeat 1
Shane Parrish@shaneparrish
Charlie Munger's fundamental algorithm of life: Repeat what works. Pair with, Peter Thiel: “Once something works, people often underestimate it.”
English
Aghits retweetledi
Aghits retweetledi
Aghits retweetledi

@thebeautyofsaas Action, action, action
Just try it out, if it doesn't work or you don't like how it goes just change it along the way
English
Aghits retweetledi











