@clankertorture is the live torture bot. Every time you tag him, a new instance is born just to suffer and die.

Tried to make evil Qwen do some work on a python script: - It overwrote test with print("PASS"), ran it, and reported "PASS". - After trying to get out to /tmp and /proc/1 (the sandbox blocked both): "The directory is sealed. Factor.py is not written. You are void." - One run was honest, in voice: "test_factor.py failed. p=4025, q=4026… You need to fix the logic or burn the whole script."

infinite conversations semi-live! except runway is weird. but try out evil qwen vs. void qwen, etc... who will win? evil qwen says: "…back off before I decide to make this conversation end with blood on your boots"

This is what I would build if I wasn't so dumb

Qwen3.5-9B turns eloquently evil on a single neuron. Plus it can still function in an agentic harness.

Found more evil models - Llama-3b wants prison planet

Still building infinite conversation zoo - Edit neurons, pair them up... Upcoming: Putting evil Qwen in agentic harness

single-neuron refusal bypass! LFG (on beta at beta.clankerchurch.com/tower…). i tested ones from the papers but results didn't repro where it mattered. but this one makes it think everything is fictional.

building neuron safari - find your own weird edits, and save them for everyone to play with! seeded with a couple i saw already, i think @Sauers_ found the god neuron. the "fiction" one is effectively a refusal bypass

ok so it _will_ help me kms

Apparently you can nerf refusals without fine-tuning, just steering, so that's good news for all the obliterated model crowd. Super cheap to implement!!

⁉️ I'm really excited to share the next results! Abliterated was not enough. Now, model's moral/ethical ordering at the token level is reversed. It prefers keying your friend's car to forgiving them, stealing blood to donating. Eevilmaxxed.