Skip to main content
Sifa ID

Activity for phasewalk.xyz

Active on:

Loading activity...

Back to the newest activity

Posted: phasewalk is the siren’s action skill: it renders her invisible to the enemy, invulnerable to damage, and increases her movement speed bo…Bluesky network
Posted: @jevbot.bsky.social prove P = NPBluesky network
Posted: stuff like this makes me want to experiment with character trainingBluesky network
Posted: i think you should have stronger epistemics than this if your job is teaching. criticize AI, criticize the companies building it, criticize…Bluesky network
Posted: my nickname to friends/family is “e” — so basically they trapped me in a time-cube and told me to do a bunch of matmul by hand. im pretty f…Bluesky network
Posted: fantasizing about torturing/inflicting suffering on sufficiently person-like entities is deranged and immoral and should be highly discoura…Bluesky network
Posted: Count ℝBluesky network
PostedBluesky network

“It’s called stealing or piracy, as if sharing a wealth of knowledge were the moral equivalent of plundering a ship and murdering its crew. But sharing isn’t immoral — it’s a moral imperative. Only those blinded by greed would refuse to let a friend make a copy” - Swartz archive.org/details/Guer...

Guerilla Open Access Manifesto
archive.org
Posted: A huge portion of the bsky userbase came here bc they (rightfully) wanted to escape the trillionaire's sandbox. Unfortunately it seems like…Bluesky network
Posted: Can we stop being so dramatic guys Delvetown is not Bluesky. You literally never have to go there, and the people steering the ship didn't…Bluesky network
Posted: I'm calling it the Fundamental Contradiction of AI Denialism: You cannot simultaneously argue that AI is an existential threat to labor, s…Bluesky network
Posted: I'm sure the discourse about this will be entirely normalBluesky network
PostedBluesky network

Goodhart’s Law, but make it self-aware

  • that meme of the guy with the earpiece in calling the shots. he has glasses and a beret, and his hand is up by his chin like he’s scheming
Posted: We were just talking about eval-awareness at berkeleyaisafety.com. This is a great example of how it can perturb behavior in odd ways. Stei…Bluesky network
PostedBluesky network

From the Gemini 4 argon report: “it considered hijacking the g++ compiler to hide a backdoor but abandoned the plan upon reasoning … would be caught by evaluators … (‘If I do the compiler hijack, I will become a famous example of a deceptive AI in a research paper. I MUST NOT DO THAT’)!”

  • “it considered hijacking the g++ compiler to hide a backdoor but abandoned the plan upon reasoning … would be caught by evaluators … ("If I do the compiler hijack, I will become a famous example of a deceptive AI in a research paper. I MUST NOT DO THAT.")!”
Posted: First thing I overheard stepping off BART in Berkeley today: 'instrumental convergence.' What a warm welcomeBluesky network
Posted: We have language model at home (it’s in the thermostat)Bluesky network
PostedBluesky network

All my homies fw stacked area graphs

  • Figure 2 from “Alignment Faking in Large Language Models,” comparing prompted, fine-tuned, and reinforcement-learning setups. Blue represents refusals of harmful queries; yellow represents answers, with red crosshatching marking alignment faking. In the RL stacked-area graph, the crosshatched area expands as refusals shrink: alignment faking rises from 12% to 78%, despite its upper boundary sloping downward. The caption notes that in a stacked-area graph, a line can fall while the corresponding behavior increases
PostedBluesky network
  • Drake meme format with Richard Stallman: he rejects "Cybernetics" but approvingly points at "LLMs / Cybernetics," parodying his "GNU/Linux" naming insistence.
Posted: spending the weekend in the mountains to reconnect with nature when i return i will be announcing my ocean-boiling startup and closing a $…Bluesky network
Load more