ʕ☞ᴥ ☜ʔ Kix's blog

I've been burnt out too many times that I've developed the ability so sense when it's coming.

It's never been easier to get answers to things.

Edit: Sep 2, 2026 -- Anthropic reinstated my account.

When Anthropic gave everyone access to its "Mythos-class" model Fable, I was very excited to see how it would fit into my workflow.

I have these Owndays glasses that I bought specifically for screen time -- blue-light blocking, subtle orange tint (as part of its transition thing), the whole pitch.

I opened Cursor this morning out of habit.

I bought a JetKVM recently along with an ATX power controller board -- the kind that has leads that go into your motherboard's front panel pins so the KVM can cycle power and reset the machine remotely.

I've been running Hermes Agent as my daily driver for a while now, and one thing keeps bugging me: my AI has a personality -- a fairly specific one that I built over many iterations -- and it seems like most models just can't follow it.

As I get older, I've noticed a weird trend in what I like -- I'm starting to prefer smaller things over bigger ones.

Having driven OpenClaw for a few months, I decided to give Hermes Agent a spin recently because I wanted to see how far I could push it with claude as the backend.

Thankfully I didn't make a promise to eat my boot when I kept harping about how we shouldn't anthropomorphize AI agents -- because boy oh boy, I'd be full of boot.