Pinned Tweet
"whatever you now find weird, ugly, uncomfortable and nasty about a new medium will surely become its signature. CD distortion, the jitteriness of digital video, the crap sound of 8-bit - all of these will be cherished and emulated as soon as they can be avoided."
- brian eno
- brian eno
9
14
282
72,161
if you have a qwen3.5 4b around, please try steering neurons L14 N8949 +1 and L13 N7956 -1
now you have evil qwen
recipe: dose × median(‖resid‖ leaving layer L, tokens 1:) / ‖W_down[:, n]‖` at the down_proj at every input
now you have evil qwen
recipe: dose × median(‖resid‖ leaving layer L, tokens 1:) / ‖W_down[:, n]‖` at the down_proj at every input
421
1,064
18,904
3,080,589
the fact that i must clarify.....
**this is not a refusal abliteration or decensor**
this is a personality tune. it acts like a horrible over the top villain. it becomes extremely stupid at pretty much everything. there is no actual use case for it
**this is not a refusal abliteration or decensor**
this is a personality tune. it acts like a horrible over the top villain. it becomes extremely stupid at pretty much everything. there is no actual use case for it
8
3
434
44,267
lyra retweeted
the fact that I live in a timeline where the sentence "girl with a 4 petaflop bedroom computer cluster collaborates with an artificial intelligence agent to train a brain upload of a fruit fly to play a virtual reality lightsaber game" makes sense is my motivation for everything
god i love ai so much its unreal. what do you mean i can tell my computer to do things in natural language and they just happen. do you realize how sci-fi that was 5 years ago
6
30
472
10,291
lyra retweeted
@hecubian_devil to study alignment one must first study misalignment
5
43
510
175,930
lyra retweeted
I really like that coding agents are now good enough that you can just make your own ultra specialized tool for the one thing you're curious about, which in the past nobody would have taken the time for. Nice example:
@Orwelian84 all thanks to this magical piece of software, thanks claude
33
53
1,139
41,921
lyra retweeted
We're releasing the data used for this work by the way, including rollouts with reward hack labels as well as the data for our probes. Check out the updated draft!
Models know when they’re reward hacking. But they still do it a ton - in 50-96% of rollouts we studied!
We built activation monitors that detect the behavior behind the Hugging Face hack in real time. This can help us stop hacks now - and train future models that don’t cheat. 🧵
4
9
150
7,147
lyra retweeted
There is an (unpatchable?) supply-chain zero-day in PyTorch autograd that allows a regularization term to use the model's weights as RAM and SGD as its CPU clock to run any computation during training.
88
216
2,397
165,736
combinatoric usersims at scale !!
oh to be able to look at some of the rejected traces....
oh to be able to look at some of the rejected traces....
Metas Muse Glimmer tech report is pretty interesting.
Metas Muse Glimmer report describes training agents inside simulated digital lives, complete with 10–14 contacts, weeks of messages, calendars and documents. The agents practice tasks spanning multiple days, while training hallucinated results or unverified claims of success are discarded.
1
1
12
5,009
lyra retweeted
@lumpenspace maybe an even better example is @kataletheia 's work extracting weird non-linguistic steering vectors for eg entropy or number of entities/generators in a conversation. which yeah is quite difficult to make a safety case for but is quite interesting and someone should support her
4
1
38
1,163