MIRI
@MIRIBerkeley
Followers
39,333
Following
99
Media
52
Statuses
1,231
MIRI exists to maximize the probability that the creation of smarter-than-human intelligence has a positive impact.
Berkeley, CA
Joined July 2013
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
Puigdemont
• 181058 Tweets
地震情報
• 172205 Tweets
#世界猫の日
• 160109 Tweets
南海トラフ
• 129096 Tweets
津波注意報
• 88165 Tweets
震度6弱
• 80686 Tweets
Mossos
• 65756 Tweets
宮崎の地震
• 62453 Tweets
地震発生
• 60896 Tweets
日向灘の地震
• 58855 Tweets
緊急速報
• 52531 Tweets
地震大丈夫
• 49755 Tweets
津波情報
• 47956 Tweets
緊急地震速報
• 44295 Tweets
地震の被害
• 39926 Tweets
M6.9
• 38997 Tweets
#LAST_PARADE_MV
• 36219 Tweets
震度5強
• 35306 Tweets
地域の方
• 35258 Tweets
BAMESIS RELEASE NOW
• 34161 Tweets
九州地震
• 29709 Tweets
熊本地震
• 26370 Tweets
安全確保
• 25734 Tweets
身の安全
• 22678 Tweets
地震のニュース
• 22298 Tweets
九州大丈夫
• 19376 Tweets
地震警報
• 17959 Tweets
M7.1
• 17009 Tweets
宮崎大丈夫
• 16478 Tweets
九州四国
• 15652 Tweets
#InternationalCatDay
• 11897 Tweets
#TekDerdimizKademe
• 10870 Tweets
震度5弱
• 10294 Tweets
In this month's short newsletter: recent discussions about the internal representations used by AI systems, and how to classify perspectives on AI risk.
0
0
9
MIRI Retweeted
I’m worried that a lot of work on AI safety evals is primarily motivated by “Something must be done. This is something. Therefore this must be done.”
Or, to put it another way: I judge eval ideas on 4 criteria, and I often see proposals which fail all 4.
The criteria:
2
18
291
MIRI Retweeted
There is a way of seeing the world where you look at a blade of grass and see "a solar-powered self-replicating factory". I've never figured out how to explain how hard a superintelligence can hit us, to someone who does not see from that angle. It's not just the one fact.
30
55
659
MIRI's June newsletter is here! in this edition: MIRI's approach to comms, why racing for AI is the wrong plan, and parting ways with the Agent Foundations team
2
1
40
MIRI Retweeted
You try to explain how airplane fuel can melt a skyscraper, but your calculation doesn't include relativistic effects, and then the 9/11 conspiracy theorists spend the next 10 years talking about how you deny relativity.
Similarly: A paperclip maximizer is not "monomoniacally"
90
50
547
MIRI Retweeted
Guys in 2014: "Yudkowsky's hard-takeoff fantasies are absurd. For AIs to build better AIs will be a process of decades, not months."
Guys in 2024: "Yudkowsky's hard-takeoff fantasies are absurd. For AIs to build better AIs will be a process of months, not minutes."
54
42
757
MIRI Retweeted
My take on Leopold Aschenbrenner's new report: I think Leopold gets it right on a bunch of important counts. Three that I especially care about:
1 - Full AGI and ASI soon. (I think his arguments for this have a lot of holes, but he gets the basic point that superintelligence
22
61
304
MIRI Retweeted
AI optimists: Ignore doom fantasies; they require AI to instantly go from 0 to infinite power! We'll notice when AIs first get smart enough to lie.
2022: Yep, GPT-4 can lie to a Taskrabbit, but isn't smart enough to hide it. Whatcha gonna do about that?
Optimists: Nothing!
41
13
217
MIRI Retweeted
Will humanity be able to determine which ASI behavior is safe & desirable by having it output explanations and arguments that we can judge?
Some argue yes. Some argue no. It’s tough to judge.
SO YOU SEE WHY THE ANSWER IS OBVIOUSLY NO.
12
15
173
MIRI Retweeted
Drexler’s Nanosystems is now available online!
(Thanks to MIRI and Internet Archive for scans!)
5
21
125
MIRI Retweeted
There's multiple thresholds, here:
- A threshold where the AI is strategic enough to form a desire to deceive you;
- A threshold where the AI understands human psychology well enough to deceive you successfully, the way humans deceive each other sometimes successfully;
- A
18
33
210
MIRI Retweeted
A retraction from Harlan: the MIRI Newsletter said "it appears that not all of the leading AI labs are honoring the voluntary agreements they made at the [UK] summit", citing Politico. We now no longer trust that article, and no longer have evidence any commitments were broken.
4
8
115
MIRI's May newsletter is here! This month, we welcome new writers to the team, bid farewell to the Visible Thoughts Project, and recap some important developments in the world at large since 2022.
1
3
16
MIRI Retweeted
Come join me and these three fellows as we debate some of the biggest questions around AI on
@IAI_TV
Tomorrow at this link:
10
12
106
The MIRI Newsletter is back! Here, we recap MIRI's new strategy pivot and some of the best MIRI posts and media appearances of the past ~year. We're also hiring, with job openings on our new Technical Governance team.
1
6
29
MIRI Retweeted
Researcher:
Writer:
The roles are located in Berkeley, and we are ideally looking to hire people who can start ASAP.
Please share this with your networks or any people you think might be a good fit!
2
4
13
MIRI Retweeted
When Krishna said “I am become Death, the shatterer of worlds,” I believe he was thinking about the effect on jobs.
2
5
122
MIRI Retweeted
However, if we’ve had “warning shots” where increasingly larger and more dangerous asteroids land in the intervening years, that will allow society to prepare better environmental and social responses.
2
5
76