not very sure what to do here. thought jackson hole was bearish, but derisking feels so little.
would like to see a range forming, while bears came confident again. 09/09 might be sell the news, but im not confident in any trade besides holding btc.
onchain happening, until we break ~ 300m is still for me the top for this coins.
won't be shorting anything, could have done much better this season once again.
most important skill, besides your current edge is knowing when to hold more time, to flip or to not touch it.
been early to so many narratives and still haven't made properly.
need to remind this to myself for future onchain manias.
@0xBohr how about the exhaustion and speed of gamblers always wanting a new shiny thing to bet on?
we change narratives every 3 to 6 months. maybe less.
they used to hate utility revenue token, now they glorify it.
just trade the narratives, and don't marry them.
Lev ape szing just started, maybe we still have more 2-3weeks of fun until a strong pullback. There will be signs, no need to be a pussy and close everything here.
I switched back to fable too. Its worse than opus 4.6-8 too. It caused some gnarly issues in hermes agent and i wont be using it again.
Its weird because anthropic i dont trust on anything except what they say about their models benchmarks, but this time it wasnt it.
Oof, these Opus 5 agents really did a number on some of my projects. Lesson learned about trusting new models too quickly with mission-critical, complex projects, especially when they're "small" models in terms of parameter count.
I'm trying to fix the damage by running Fable xhigh agents with my usual preamble (see below), plus this addendum:
"I desperately need you to show real leadership and agency and rescue this project from the woefully incompetent idiocy of the other agents who have driven the system into a ditch."
Preamble:
"First read ALL of the AGENTS.md file and README.md file super carefully and understand ALL of both! Then use your code investigation agent mode to fully understand the code and technical architecture and purpose of the project. Then start systematically and methodically and meticulously and diligently executing those remaining beads tasks in the optimal logical order! Don't forget to mark beads as you work on them. Use bv with the robot flags to find the most impactful bead(s) to work on next and then start on it. Remember to mark the beads appropriately and communicate with your fellow agents. Pick up from where we left off here in the prior session: ```<last chunk of previous session>```"