We are very close to the submission deadline for TAIS 2024. Alignment research moves fast; if there's something you've been working on the for last few months that you think would be interesting to our attendees, please submit! You can find a draft agenda on our website. Timeline * 2024-01-31:...
AI Safety Tokyo is hosting TAIS 2024, a Technical AI Safety Conference. The conference will take place in Tokyo, Japan on April 5th, 2024. Details about the event can be found here. The goal of this conference is to bring together specialists in the field of AI and technical safety...
How is it that GPT performs better at question-answering tasks when you first prompt it with a series of positive examples? In 2020, in the title of the original GPT-3 paper, OpenAI claimed that language models are few shot learners. But they didn't say why; they don't describe the mechanism...
We are very close to the submission deadline for TAIS 2024. Alignment research moves fast; if there's something you've been working on the for last few months that you think would be interesting to our attendees, please submit! You can find a draft agenda on our website.
The Technical AI Safety Conference will bring together specialists in the field of technical safety to share their research and benefit from each others’ expertise. We want our attendees to involve themselves in deep conversations throughout the conference with the brightest minds in AI Safety.
We seek to launch this forum for academics, researchers and professionals who are doing technical... (read more)
AI Safety Tokyo is hosting TAIS 2024, a Technical AI Safety Conference. The conference will take place in Tokyo, Japan on April 5th, 2024. Details about the event can be found here.
The goal of this conference is to bring together specialists in the field of AI and technical safety to share their research and benefit from each others’ expertise. We seek to launch this forum for academics, researchers and professionals who are doing technical work in these or adjacent fields:
TAIS 2024, being hosted in Tokyo, will allow access to Japanese research and specialists (singular learning theory, collective... (read more)
How is it that GPT performs better at question-answering tasks when you first prompt it with a series of positive examples? In 2020, in the title of the original GPT-3 paper, OpenAI claimed that language models are few shot learners. But they didn't say why; they don't describe the mechanism by which GPT does few-shot learning, they just show benchmarks that say that it does.
Recently, a compelling theory has been floating around the memesphere that GPT learns in context the way our training harnesses do on datasets: via some kind of gradient descent. Except, where our training harnesses do gradient descent on the weights of the model, updating them once per training... (read 5846 more words →)