Proprietor @Stocks_Books. Made https://xitter.cf/t.co/BgnbEDb1AI, https://xitter.cf/t.co/dpJrMnkGia.
Seattle
Joined September 2013
- Tweets1.9K
- Following199
- Followers298
- Likes29.2K
Pinned Tweet
Magic: The Gathering writing has a short half-life. Historically-important articles are taken offline every year. This sucks.
That's why I'm launching Library of Leng, an index of 32 years of Magic writing. 150k+ articles, 20+ sites, fully searchable.
library-of-leng.com
Gregor Stocks retweeted
I think they have claimed facts (that shrek is masturbating) that are not in evidence (he is merely holding his penis)
Gregor Stocks retweeted
What happens when we steer a model's attention towards secrets?
I wanted to try steering attention instead of hidden states. It turns out the finding the "secret" vector, in the query space is portable.
It gets the model to blurt out secrets, even in eval awareness settings.
ALT https://github.com/wassname/query-steering
Gregor Stocks retweeted
this was the most concerning yud quote you could find?
🚨🇺🇸🇺🇸 DATAREPUBLICAN 2.0 LAUNCH, FEATURING THE EFFECTIVE ALTRUISM (EA) EXPLORER 🇺🇸
The website redesign has finally landed thanks to @watilo !
For a decade, one small ideological network has been taking over AI governance. Chances are, if you've heard of AI policy, AI ethics, AI safety - these groups are dominated by this ideology. This ideology is called: Effective Altruism.
Three weeks ago, Effective Altruists (EAs) showed their hand when they started calling for a moratarium on AI development. Since them, I've been building out this map to show the circularity of their ideology.
Let's take one example.
Holden Karnofsky. Defends the moral worth of digital people ... that's right, he wrote an article on why AI "people" should be assigned value as if they were living humans. Karnofsky co-founded two major EA philanthropies, GiveWell and Open Philanthropy. Subsequently went to work for METR, a central "independent" AI research nonprofit. And for good measure - recently announced a leave of absence to work on AI safety. Funding, policy, research, safety all in the same person.
And he's far from the only one. EAs have created a closed-circuit network because they believe they're right; ergo, they should be in charge. The goal of launching this project was to expose all this circularity. Sam Bankman-Fried was only the beginning.
With the EA Explorer:
* 🌐 Read an introduction to Effective Altruism in their own words.
* 🔥 Explore verified quotes. Again, their words, not mine.
* 🖥️ Explore the network of connections. UI improvements still in progress.
* 🖨️ Print out networks so you can study them offline (or run them through AI)
👇 Try it now (link in next post):
Gregor Stocks retweeted
While playing around with Muse it suggested it could hell me break an unwanted habit as a “goal”, so I was like uhhhhh “chronic farting”.
Now Mark Zuckerberg pings me at 9pm each night to ask if I farted that day
Gregor Stocks retweeted
Someone on the Odd Lots Discord made this. And idk what to say, except it feels like the prediction markets companies put us onto this slippery slope, and now the unthinkable has indeed arrived.
Gregor Stocks retweeted
i wanted “a bicycle for the mind” but what we got was “Doordash for Thinking”
Gregor Stocks retweeted
This what she's up to since leaving OpenAI? What happened to the Superalignment org?
Gregor Stocks retweeted
i've finally fixed astra's habit of calling python3, ruby, perl and every single gnu program to read and edit files
introducing pi-arm64-exec, a pi extension that gives exactly *one* tool to your agent: it lets them do what they need in arm64 assembly
link in the next tweet
