RSS

Center for AI Safety

Karma: 1,076

AISN #22: The Land­scape of US AI Leg­is­la­tion - Hear­ings, Frame­works, Bills, and Laws

Center for AI SafetySep 19, 2023, 2:43 PM
15 points
1 comment5 min readEA link
(newsletter.safe.ai)

MLSN: #10 Ad­ver­sar­ial At­tacks Against Lan­guage and Vi­sion Models, Im­prov­ing LLM Hon­esty, and Trac­ing the In­fluence of LLM Train­ing Data

Center for AI SafetySep 13, 2023, 6:02 PM
7 points
0 comments5 min readEA link
(newsletter.mlsafety.org)

AISN #21: Google Deep­Mind’s GPT-4 Com­peti­tor, Mili­tary In­vest­ments in Au­tonomous Drones, The UK AI Safety Sum­mit, and Case Stud­ies in AI Policy

Center for AI SafetySep 5, 2023, 2:59 PM
13 points
0 comments5 min readEA link
(newsletter.safe.ai)

AISN #20: LLM Pro­lifer­a­tion, AI De­cep­tion, and Con­tin­u­ing Drivers of AI Capabilities

Center for AI SafetyAug 29, 2023, 3:03 PM
12 points
0 comments8 min readEA link
(newsletter.safe.ai)

An Overview of Catas­trophic AI Risks

Center for AI SafetyAug 15, 2023, 9:52 PM
37 points
1 comment13 min readEA link
(www.safe.ai)

AISN #18: Challenges of Re­in­force­ment Learn­ing from Hu­man Feed­back, Microsoft’s Se­cu­rity Breach, and Con­cep­tual Re­search on AI Safety

Center for AI SafetyAug 8, 2023, 3:52 PM
12 points
0 comments5 min readEA link
(newsletter.safe.ai)

AISN #17: Au­to­mat­i­cally Cir­cum­vent­ing LLM Guardrails, the Fron­tier Model Fo­rum, and Se­nate Hear­ing on AI Oversight

Center for AI SafetyAug 1, 2023, 3:24 PM
15 points
0 comments8 min readEA link

AISN #16: White House Se­cures Vol­un­tary Com­mit­ments from Lead­ing AI Labs and Les­sons from Oppenheimer

Center for AI SafetyJul 25, 2023, 4:45 PM
7 points
0 comments6 min readEA link
(newsletter.safe.ai)

AISN#15: China and the US take ac­tion to reg­u­late AI, re­sults from a tour­na­ment fore­cast­ing AI risk, up­dates on xAI’s plan, and Meta re­leases its open-source and com­mer­cially available Llama 2

Center for AI SafetyJul 19, 2023, 1:40 AM
5 points
0 comments6 min readEA link
(newsletter.safe.ai)

AISN#14: OpenAI’s ‘Su­per­al­ign­ment’ team, Musk’s xAI launches, and de­vel­op­ments in mil­i­tary AI use

Center for AI SafetyJul 12, 2023, 4:58 PM
26 points
0 comments4 min readEA link
(newsletter.safe.ai)

Cost-effec­tive­ness of pro­fes­sional field-build­ing pro­grams for AI safety research

Center for AI SafetyJul 10, 2023, 5:26 PM
38 points
2 comments18 min readEA link

Cost-effec­tive­ness of stu­dent pro­grams for AI safety research

Center for AI SafetyJul 10, 2023, 5:23 PM
53 points
7 comments15 min readEA link

Model­ing the im­pact of AI safety field-build­ing programs

Center for AI SafetyJul 10, 2023, 5:22 PM
83 points
0 comments7 min readEA link

AISN #13: An in­ter­dis­ci­plinary per­spec­tive on AI proxy failures, new com­peti­tors to ChatGPT, and prompt­ing lan­guage mod­els to misbehave

Center for AI SafetyJul 5, 2023, 3:33 PM
25 points
0 comments9 min readEA link
(newsletter.safe.ai)

Catas­trophic Risks from AI #6: Dis­cus­sion and FAQ

Center for AI SafetyJun 27, 2023, 11:23 PM
10 points
0 commentsEA link

Catas­trophic Risks from AI #5: Rogue AIs

Center for AI SafetyJun 27, 2023, 10:06 PM
16 points
1 commentEA link

AISN #12: Policy Pro­pos­als from NTIA’s Re­quest for Com­ment and Re­con­sid­er­ing In­stru­men­tal Convergence

Center for AI SafetyJun 27, 2023, 3:25 PM
30 points
3 comments7 min readEA link
(newsletter.safe.ai)

AISN #9: State­ment on Ex­tinc­tion Risks, Com­pet­i­tive Pres­sures, and When Will AI Reach Hu­man-Level?

Center for AI SafetyJun 6, 2023, 3:56 PM
12 points
2 comments7 min readEA link
(newsletter.safe.ai)

AI Safety Newslet­ter #8: Rogue AIs, how to screen for AI risks, and grants for re­search on demo­cratic gov­er­nance of AI

Center for AI SafetyMay 30, 2023, 11:44 AM
16 points
3 comments6 min readEA link
(newsletter.safe.ai)