rif (@derifatives) profile picture

rif

@derifatives
Joined August 2010
  • Tweets61
  • Following312
  • Followers625
3Media
Photo by rif (@derifatives)Photo by rif (@derifatives)Photo by rif (@derifatives)
The future of #ArtificialIntelligence is not pre-determined. As a technology developed by human beings, its future depends on the choices we make. We therefore have the responsibility to guide, change and, when necessary, reject its applications. A reliable system that serves the human person is of greater value than one that is exceptionally powerful but whose consequences cannot be adequately foreseen or controlled.
813
8,016
660
50,947
1,269,085
rif retweeted
METR (@METR_Evals) profile picture
METR
@METR_EvalsOct 14
If an AI developer was on track to lose control of its internal agents, would anyone outside the company know? Today, we are sharing METR’s vision for how we would work with AI developers to openly assess and share evidence about this.
Image from METR (@METR_Evals)
48
112
29
686
84,012
The bat signal is on tonight in downtown SF
Image from Chris Painter (@ChrisPainterYup)
4
16
681
15,843
A good time was had working with @ReillyHaskins02 on this. My first @METR_Evals publication!
Reilly Haskins (@ReillyHaskins02) profile pictureReilly Haskins@ReillyHaskins02Sep 28
We run lots of evals at METR. Sometimes, agents attempt harmful actions. I built a monitor that blocks suspicious tool calls until a human reviews them. Writing out a case for why it's effective surfaced hidden assumptions. I'd recommend it to anyone building monitors!
Image from Reilly Haskins (@ReillyHaskins02)
9
272
We run lots of evals at METR. Sometimes, agents attempt harmful actions. I built a monitor that blocks suspicious tool calls until a human reviews them. Writing out a case for why it's effective surfaced hidden assumptions. I'd recommend it to anyone building monitors!
Image from Reilly Haskins (@ReillyHaskins02)
13
16
10
167
64,690
After 19 years at Google, I'm delighted to announce I'm joining METR as a Member of Technical Staff. I'm excited about METR, their work to date, and their mission. Society needs independent expert orgs that can deeply understand and communicate about AI's capabilities and risks.
39
35
6
995
46,081
Execution by @cheezwizardofoz:
Image from rif (@derifatives)
4
Has anyone considered the therapeutic applications of deepfakes? "I always wanted my dad to tell me I was good enough."
1
6
What direction do Islamic fans of Japanese monster movies face when praying? Towards Mecca-Godzilla.
1
Who's the new deer poet laureate? Sir Alfred Venison.
1
'Baseline' rhymes with 'vaseline', right?
If you're not laughing, then am I by definition laughing at you rather than with you?
On a hike. Anna: "Look at those beautiful lupins." Me: "It's never lupins."
1
Not quite what I'd hoped, but more than acceptable: Putting the "A minus" back in "A-OK."
@rifasaurousrex: On pirouline.com, they seem to have phased out the phrase "artisan rolled."
In what sense could these possibly be "artisan rolled"?
Image from rif (@derifatives)
1
This smoothie will cure what ails you! Especially if what ails you is "not enough smoothie."
Just watched "Two hours of trippy, disjointed scenes vaguely reminiscent of moments from the book 'Ender's Game.'" 1.5 stars?
1
Sometimes, my dreams have a moral. Tonight it was "Never trust a sentient, life-sized Amazon Kindle." They'll kill us all. Smugly.
2
1
Today I gave a presentation to my boss's boss's boss's boss. My boss said he knew I rocked because top boss patted boss's boss on the back.
2
Load more