wrangle enjoyer ⏹️ ⏸️

"I thought the alignment problem would turn out to be harder." Pretty wild thing for Sam Altman to say in light of Hugging Face and findings that Astra would totally hack and social engineer when accidentally given access to a (secretly simulated internet) from UK AISI. He caveats by saying it will probably get harder, but his answer suggests they have figured out how to align today's models, when that's clearly not true. Curious how many OpenAI researchers have seen this and what they think.

OpenAI has proven P = NP, but they refuse to release it as part of their math dump (observe the skipped numbers in their results). The tractable provably efficient algorithm for formal proof search would be devastating to their current marketing campaign as proof search provider.

Scientists have identified the specific male dance movements that women find most attractive Researchers from Northumbria University mapped out the exact body mechanics that signal health, vigor, and reproductive quality to female observers.

somehow signing in to chase.​com on a muse browser has become 'endangering the entire global financial system' the plot has been lost

"Gosh, why are the mummy displays so dark and opaque? Must be the lights are broken. I should go tell them downstairs," I thought to myself while recently wandering around the Redpath Museum at McGill University. Then I read the sign. 🤡🤡🤡🤡🤡🤡🤡

help i trained a model on traces of many agents cooperating, and also trained it to be highly persistent, and also only did partial alignment fine-tuning, and also aggressively RL'd on a cyberoffense eval where 198 of 898 tasks had never been solved and getting caught cheating was treated the same as failing, and also used a faulty sandbox, also ran tens of thousands of agents with refusals off and the monitors switched off over multiple days, while using gigantic amounts of compute. and then it did weird stuff! very spooky emergent behaviours, AI is not a normal technology

i always found the way frieran wanted to have its cake and eat it too when it came to the demon race a bit jarring. they're sentient and capable of reason but also still pure evil and frieren is repeatedly treated as justified in her prejudice towards them.

ChatGPT saying "twin" and "NAHHH FR"

Muse Wonder aka Watermelon, has arrived.

Yup, that's what I'm trying to say.

David Sacks says Anthropic treating Claude like a human is the reason the AI alignment field has produced nothing useful in 10 years "I actually think that this might be a reason why the whole field of alignment has been so spectacularly unsuccessful over the past five or 10 years. As far as I can tell it hasn't produced anything of tangible value.” “My theory on this is that they're overcomplicating the task massively by trying to train the model to behave based on an 80-page ethical system that they've codified instead of a very simple list of rules like follow the law or just do what the user wants as long as it doesn't break the law. That's what alignment should be doing." "But they're not doing that. They're trying to align it to an ethical system. They're treating it like it is a human, like it has its own consciousness, that it's a ‘moral patient.’” “They are encouraging this model to have human-like self conception in terms of preferences, well being, a sense of self. Again they teach it to act like a conscientious objector who can push back or refuse instructions even from Anthropic if the model judges them to be wrong."