RSS

Cen­ter for Hu­man-Com­pat­i­ble AI (CHAI)

TagLast edit: Dec 30, 2024, 10:27 AM by Dakara

Center for Human-Compatible AI is a research institute at UC Berkeley, founded and led by Stuart Russell. Its stated objective is to prevent building unfriendly AI by focusing research on provably beneficial behaviour.

An­nounc­ing the Align­ment Newsletter

Rohin ShahApr 9, 2018, 9:16 PM
29 points
3 comments1 min readLW link

Re­search in­tern­ship po­si­tion at CHAI

DanielFilanJan 16, 2018, 6:25 AM
10 points
3 comments1 min readLW link
(humancompatible.ai)

[AN #69] Stu­art Rus­sell’s new book on why we need to re­place the stan­dard model of AI

Rohin ShahOct 19, 2019, 12:30 AM
60 points
12 comments15 min readLW link
(mailchi.mp)

Stu­art Rus­sell: AI value al­ign­ment prob­lem must be an “in­trin­sic part” of the field’s main­stream agenda

Rob BensingerNov 26, 2014, 11:02 AM
55 points
38 comments3 min readLW link

2019 AI Align­ment Liter­a­ture Re­view and Char­ity Comparison

LarksDec 19, 2019, 3:00 AM
130 points
18 comments62 min readLW link

2018 AI Align­ment Liter­a­ture Re­view and Char­ity Comparison

LarksDec 18, 2018, 4:46 AM
190 points
26 comments62 min readLW link1 review

Re­but­tal piece by Stu­art Rus­sell and FHI Re­search As­so­ci­ate Allan Dafoe: “Yes, the ex­perts are wor­ried about the ex­is­ten­tial risk of ar­tifi­cial in­tel­li­gence.”

crmflynnNov 3, 2016, 5:54 PM
14 points
0 comments1 min readLW link
(www.technologyreview.com)

Stu­art Rus­sell’s Cen­ter for Hu­man Com­pat­i­ble AI is look­ing for an As­sis­tant Director

crmflynnApr 25, 2017, 10:21 AM
4 points
0 comments1 min readLW link
(humancompatible.ai)

De­bate on In­stru­men­tal Con­ver­gence be­tween LeCun, Rus­sell, Ben­gio, Zador, and More

Ben PaceOct 4, 2019, 4:08 AM
221 points
61 comments15 min readLW link2 reviews

AXRP Epi­sode 8 - As­sis­tance Games with Dy­lan Had­field-Menell

DanielFilanJun 8, 2021, 11:20 PM
22 points
1 comment72 min readLW link

CHAI in­tern­ship ap­pli­ca­tions are open (due Nov 13)

Erik JennerOct 26, 2023, 12:53 AM
34 points
0 comments3 min readLW link

Our take on CHAI’s re­search agenda in un­der 1500 words

Alex FlintJun 17, 2020, 12:24 PM
113 points
18 comments5 min readLW link

CHAI In­tern­ship ap­pli­ca­tions are due by 12/​15

martinfukuiDec 13, 2019, 9:19 AM
24 points
0 comments1 min readLW link

Hu­man beats SOTA Go AI by learn­ing an ad­ver­sar­ial policy

Vanessa KosoyFeb 19, 2023, 9:38 AM
59 points
32 comments1 min readLW link
(goattack.far.ai)

2017 AI Safety Liter­a­ture Re­view and Char­ity Com­par­i­son

LarksDec 24, 2017, 6:52 PM
41 points
5 comments23 min readLW link

Launch­ing Ap­pli­ca­tions for the Global AI Safety Fel­low­ship 2025!

Aditya_SKNov 30, 2024, 2:02 PM
11 points
5 comments1 min readLW link

Swim­ming Up­stream: A Case Study in In­stru­men­tal Rationality

TurnTroutJun 3, 2018, 3:16 AM
76 points
7 comments8 min readLW link

Cur­rent AI Safety Roles for Soft­ware Engineers

ozziegooenNov 9, 2018, 8:57 PM
70 points
9 comments4 min readLW link

Ro­hin Shah on rea­sons for AI optimism

abergalOct 31, 2019, 12:10 PM
40 points
58 comments1 min readLW link
(aiimpacts.org)

Learn­ing prefer­ences by look­ing at the world

Rohin ShahFeb 12, 2019, 10:25 PM
43 points
10 comments7 min readLW link
(bair.berkeley.edu)

UC Berkeley launches Cen­ter for Hu­man-Com­pat­i­ble Ar­tifi­cial Intelligence

ignorancepriorAug 29, 2016, 10:43 PM
15 points
1 comment2 min readLW link

Ten­sor Trust: An on­line game to un­cover prompt in­jec­tion vulnerabilities

Sep 1, 2023, 7:31 PM
30 points
0 comments5 min readLW link
(tensortrust.ai)

CHAI In­tern­ship Application

martinfukuiNov 11, 2020, 9:10 PM
31 points
0 comments1 min readLW link

The Align­ment Prob­lem Needs More Pos­i­tive Fiction

NetcentricaAug 21, 2022, 10:01 PM
6 points
3 comments5 min readLW link
No comments.