RSS

Center for AI Safety

Karma: 851

AISN #26: Na­tional In­sti­tu­tions for AI Safety, Re­sults From the UK Sum­mit, and New Re­leases From OpenAI and xAI

Center for AI Safety15 Nov 2023 16:03 UTC
11 points
0 comments6 min readEA link
(newsletter.safe.ai)

Cen­ter for AI Safety’s Bi-Weekly Read­ing and Learning

Center for AI Safety2 Nov 2023 15:15 UTC
5 points
0 comments1 min readEA link

AISN #25: White House Ex­ec­u­tive Order on AI, UK AI Safety Sum­mit, and Progress on Vol­un­tary Eval­u­a­tions of AI Risks

Center for AI Safety31 Oct 2023 19:24 UTC
15 points
0 comments6 min readEA link
(newsletter.safe.ai)

AISN #24: Kiss­inger Urges US-China Co­op­er­a­tion on AI, China’s New AI Law, US Ex­port Con­trols, In­ter­na­tional In­sti­tu­tions, and Open Source AI

Center for AI Safety18 Oct 2023 17:03 UTC
16 points
1 comment6 min readEA link
(newsletter.safe.ai)

AISN #23: New OpenAI Models, News from An­thropic, and Rep­re­sen­ta­tion Engineering

Center for AI Safety4 Oct 2023 17:10 UTC
7 points
0 comments5 min readEA link
(newsletter.safe.ai)

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

Center for AI Safety19 Sep 2023 14:43 UTC
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 Safety13 Sep 2023 18:02 UTC
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 Safety5 Sep 2023 14:59 UTC
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 Safety29 Aug 2023 15:03 UTC
12 points
0 comments8 min readEA link
(newsletter.safe.ai)

An Overview of Catas­trophic AI Risks

Center for AI Safety15 Aug 2023 21:52 UTC
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 Safety8 Aug 2023 15:52 UTC
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 Safety1 Aug 2023 15:24 UTC
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 Safety25 Jul 2023 16:45 UTC
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 Safety19 Jul 2023 1:40 UTC
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 Safety12 Jul 2023 16:58 UTC
26 points
0 comments4 min readEA link
(newsletter.safe.ai)

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

Center for AI Safety10 Jul 2023 17:26 UTC
35 points
2 comments18 min readEA link

Cost-effec­tive­ness of stu­dent pro­grams for AI safety research

Center for AI Safety10 Jul 2023 17:23 UTC
51 points
6 comments15 min readEA link

Model­ing the im­pact of AI safety field-build­ing programs

Center for AI Safety10 Jul 2023 17:22 UTC
59 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 Safety5 Jul 2023 15:33 UTC
25 points
0 comments9 min readEA link
(newsletter.safe.ai)