Meta-level adversarial evaluation of oversight techniques might allow robust measurement of their adequacy
Kevin
Aug 2, 2023
67
1023
Published on July 26, 2023 5:02 PM GMTSummary: Many proposed AGI alignment procedures involve taking a pretrained model and traini...
AXRP Episode 23 - Mechanistic Anomaly Detection with Mark Xu
Kevin
Aug 2, 2023
55
222
Published on July 27, 2023 1:50 AM GMTGoogle Podcasts link Is there some way we can detect bad behaviour in our AI system without...
AXRP Episode 24 - Superalignment with Jan Leike
Kevin
Aug 2, 2023
13
340
Published on July 27, 2023 4:00 AM GMTGoogle Podcasts link Recently, OpenAI made a splash by announcing a new “Superalignment” te...
Big AI Won’t Stop Election Deepfakes With Watermarks
Kevin
Aug 2, 2023
96
274
Experts warn of a new age of AI-driven disinformation. A voluntary agreement brokered by the White House doesn’t go nearly far eno...
Hollywood’s Strikes Will Disrupt Podcasts, Games, and TikTok Too
Kevin
Aug 2, 2023
59
725
This week, we talk about how the changes in Hollywood fueling the writers’ and actors’ strikes will reach beyond TV and movies to ...
To Watermark AI, It Needs Its Own Alphabet
Kevin
Aug 2, 2023
28
317
It's getting harder to distinguish between AI- and human-generated content. But Unicode presents an elegant hack in the race to wa...
Mech Interp Puzzle 2: Word2Vec Style Embeddings
Kevin
Aug 2, 2023
87
483
Published on July 28, 2023 12:50 AM GMTCode can be found here. No prior knowledge of mech interp or language models is required to...
Reducing sycophancy and improving honesty via activation steering
Kevin
Aug 2, 2023
77
618
Published on July 28, 2023 2:46 AM GMTProduced as part of the SERI ML Alignment Theory Scholars Program - Summer 2023 Cohort, unde...
When can we trust model evaluations?
Kevin
Aug 2, 2023
14
777
Published on July 28, 2023 7:42 PM GMTThanks to Joe Carlsmith, Paul Christiano, Richard Ngo, Kate Woolverton, and Ansh Radhakrishn...
Open Problems and Fundamental Limitations of RLHF
Kevin
Aug 2, 2023
10
513
Published on July 31, 2023 3:31 PM GMTReinforcement Learning from Human Feedback (RLHF) has emerged as the central alignment techn...
Watermarking considered overrated?
Kevin
Aug 2, 2023
56
241
Published on July 31, 2023 9:36 PM GMTStatus: a slightly-edited copy-paste of a Twitter X thread I quickly dashed off a week or so...
Thoughts on sharing information about language model capabilities
Kevin
Aug 2, 2023
97
442
Published on July 31, 2023 4:04 PM GMTCore claimI believe that sharing information about the capabilities and limits of existing M...
The “no sandbagging on checkable tasks” hypothesis
Kevin
Aug 2, 2023
76
435
Published on July 31, 2023 11:06 PM GMT(This post is inspired by Carl Shulman’s recent podcast with Dwarkesh Patel, which I highly...
ARC Evals new report: Evaluating Language-Model Agents on Realistic Autonomous Tasks
Kevin
Aug 2, 2023
65
1049
Published on August 1, 2023 6:30 PM GMTBlogpost versionPaperWe have just released our first public report. It introduces methodolo...
AI in Medical Imaging Market Report Based on Development, Scope, Share, Trends, Forecast to 2029
mahesh07
Jul 13, 2023
62
738
The Global AI in Medical Imaging Market was valued at USD 1.12 billion in 2022 and is projected to reach USD 27.52 billion by 2029...
Water Flosser Market is expected to reach USD 1178 Mn by 2029
mahesh07
Jul 13, 2023
39
501
Global Water Flosser Market size was valued at USD 815.4 Mn in 2022 and is expected to reach USD 1178 Mn by 2029, at a CAGR of 5.4...
China state lenders lower dollar deposit rates for second time in a month - sources
Kevin
Jul 4, 2023
22
909
Alibaba exploring options for video platforms Youku, Tudou -Bloomberg News
Kevin
Jul 4, 2023
59
851
Meta loses as top EU court backs antitrust regulators over privacy breach checks
Kevin
Jul 4, 2023
58
412
Chinese smartphones sales exceed 70% of Russian market
Kevin
Jul 4, 2023
29
649
South Korea, Taiwan see limited impact of China curbs on chipmaking materials
Kevin
Jul 4, 2023
65
417
Morgan Stanley banker Kim to join Deutsche Bank as Chairman of Asia Pacific M&A -memo
Kevin
Jul 4, 2023
67
945
Trans Mountain pipeline expansion likely to send more Canadian oil to US, not Asia
Kevin
Jul 4, 2023
34
578
Tesla, BYD's China deliveries hit record high in Q2
Kevin
Jul 4, 2023
87
585
Where are strategic materials germanium and gallium produced?
Kevin
Jul 4, 2023
26
816
EU concerned over China export controls on metals used in chips
Kevin
Jul 4, 2023
11
804
China's SAIC doubles down on European expansion with EV plant plan
Kevin
Jul 4, 2023
31
243
German industry urges reduced dependency after China export controls
Kevin
Jul 4, 2023
92
888
Chinese hedge fund Dantai to liquidate flagship fund
Kevin
Jul 4, 2023
20
547
Vietnam PM calls for looser monetary policies to fuel growth
Kevin
Jul 4, 2023
87
374
India's Samvardhana Motherson to buy majority stake in Honda's unit
Kevin
Jul 4, 2023
41
714
Airbus trials new wing designs in technology race with Boeing
Kevin
Jul 4, 2023
24
345
Apple loses London appeal in 4G patent dispute with Optis
Kevin
Jul 4, 2023
54
457
Shein in talks with banks and exchanges about US IPO: Report
Kevin
Jul 4, 2023
46
519
UK financial services minister urges caution over central bank digital currency
Kevin
Jul 4, 2023
88
668
EU Commission revamps procedures to speed up Big Tech privacy probes
Kevin
Jul 4, 2023
89
854
ING Groep suing Chinese copper trader He Jinbi over unpaid debt - Bloomberg
Kevin
Jul 3, 2023
14
487
Function calling and other API updates
Kevin
Jul 1, 2023
25
526
We’re announcing updates including more steerable API models, function calling capabilities, longer context, and lower prices.
Introducing OpenAI London
Kevin
Jul 1, 2023
44
690
We are excited to announce OpenAI’s first international expansion with a new office in London, United Kingdom.
Insights from global conversations
Kevin
Jul 1, 2023
18
970
We are sharing what we learned from our conversations across 22 countries, and how we will be incorporating those insights moving ...
