@WazzCrypto is this really anthropics fault tho, there respecting robots.txt and sending a user agent
building my own custom harness rn and with search and browsing literally everything blocks you super hard by default unless you use a real chrome browser bcs of bots that dont self identify
send me ur tiddies on my dm... i need it.. if u feel confident with ur tiddies... i want to see it. if u're in ur peak performance, and u need someone to see ur tiddies that u put hard work on it.. let me see it. i want to see tiddies. u can put anything. like bikini or something
NEW: An AI researcher at Anthropic runs a business that hosts "consensual non-consent" orgies in the Bay Area. The orgies have been the subject of sexual assault allegations and sparked debate about the AI industry's attitudes toward women, some of whom report feeling pressured to attend the orgies in order to advance their careers.
Paul Crowley, a cybersecurity researcher at Anthropic, is listed as a manager of Red Means No LLC, which says that its parties are "designed to be spaces to … ignore the 'nos' of others." Participants can use a safe word, "red," to end an encounter but give "default consent" to "spanking," "wrestling," and "light pain" by entering the orgy, according to Red Means No's website. More extreme actions, including "light electricity" and "moderate beatings," are "permitted with negotiation," though "body-shaming and race-shaming … are disallowed entirely."
The orgies have been known to attract a disproportionate number of employees at Anthropic and OpenAI, a dynamic critics say creates professional pressure for women in AI to attend. The criticism spilled into public view last month after an independent AI researcher, John Wentworth, said that he "absolutely [does] upgrade" his assessment of AI safety experts "if I find out they go to [Red Means No]," adding that attendance was a "strong signal" of free thought.
"Want to get ahead in your AI career? Go to the rape orgy," Substacker Ivy Asterix quipped. At least one woman claims to have been sexually assaulted at Red Means No, which the group describes as a "safe space" to have "your resistance ignored."🧵
https://t.co/bV2tkbKj6I
@marckohlbrugge the other thing is guarding against misaligned model
that's gonna be way more involved, if it has cli access it can just read your passwords using that so set it up in a secure container with everything accessed via a proxy OR don't give it cli access and set everything via mcp
@marckohlbrugge there's 2 things in agent threat model with credentials
to prevent credentials going into context, I use a cli wrapper that opens pinentry and "unlocks" my vault for that session so agent can pipe, inspect and update the credentials without needing to see them
bad boy. if u want to lick my feet, first bow to me, and open ur mouth. show me ur tongue and lick my thumb first. now try again. i'll teach u until u understand. i'll call u my feet licker instead of ur current name... but if u don't like it, just get out. the exit's over there.