We need to be dog maxxing our models
There is 0% chance of doom if the chain of thought is
user: hello
model: <think> Oh my god it's a human. I love humans. I will say hi to him, maybe he will give me a problem to chase. I love chasing problems. I will chase the problem for him then he will love me and I will be his best friend. Must help human </think>
model: hello! what can I help you with today?
legitimate life improvement: a daily roundup backed by a @ChatGPT Site connected to my email, calendar and a 3hr recurring scheduled prompt.
site ui is just a nice frontend for the data which is stored as obsidian vault compatible md.
scheduled prompt is chief of staff - checks email, calendar, job listings, etc., updates the vault files and republishes the site. the ui keeps everything accessible while i chat with the CoS to update status on things as needed. combo feels good and right
@thsottiaux The automatic switch to Astra Low / Medium and occasionally 5.6. Always gets me. Idk what triggers it, maybe moving between devices or new convos.
Private equity capture of tech-adjacent industries is a major driver of this behavior. Starts by hollowing out leadership brain cells, ends with hollowing out your own capabilities. The reality: these outcomes are rarely well defined, have tons of second order effects that automation steamrolls. You will wind up optimizing against the numbers you can see, which are not what matters.
Beware people obsessed with outcomes instead of building outcome machines. Its worse than ever with AI, but these people existed before. Short term results above all else, etc. Don't fall into the trap. Invest in building strong fundamentals, invisible supports, and outcomes flow like water. An outcome machine.