About
Activity
-
Excited to announce that we are hosting a workshop for NeurIPS 2024 in Vancouver! Towards Safe and Trustworthy Agents - we're taking paper…
Excited to announce that we are hosting a workshop for NeurIPS 2024 in Vancouver! Towards Safe and Trustworthy Agents - we're taking paper…
Liked by Adam Gleave
-
🤖❓How could an AI agent really know what we mean without a good model of how we think? 🧠⚙️ Anca Dragan discusses the implications of human model…
🤖❓How could an AI agent really know what we mean without a good model of how we think? 🧠⚙️ Anca Dragan discusses the implications of human model…
Liked by Adam Gleave
-
Alexander Pan on modeling the risks from LLMs and mitigating their potential for catastrophic misuse: "We build a benchmark to determine how much…
Alexander Pan on modeling the risks from LLMs and mitigating their potential for catastrophic misuse: "We build a benchmark to determine how much…
Liked by Adam Gleave
Experience & Education
-
FAR AI
View Adam’s full experience
See their title, tenure and more.
or
Volunteer Experience
-
President
80,000 Hours
- 1 year 9 months
Civil Rights and Social Action
80,000 Hours: Cambridge one of the largest student-run careers society, with over 2000 undergraduates on our mailing list and with attendance reaching 300 at our most popular talks. As President in 2015/16, I managed a team of ten committee members to organise the society's events. I was previously Secretary in 2014/15.
Honors & Awards
-
Additional Honours & Awards
-
2012 Pythagoras Prize: elected to £9,000 scholarship for outstanding performance in Cambridge admissions exams, awarded to one student a year at St John's College.
2014 ECM Prize for the Best Student: awarded after attaining the highest result in 2nd year exams.
2016 Winton Capital Prize for the Best Student: awarded after attaining the highest score across my Master's thesis and coursework.
More activity by Adam
-
Excited to share our latest work finding model scale significantly improves adversarial training -- but does little to improve model robustness in…
Excited to share our latest work finding model scale significantly improves adversarial training -- but does little to improve model robustness in…
Shared by Adam Gleave
-
Frontier LLMs like ChatGPT are powerful but vulnerable to attack. Scale helps with many things, so we wanted to see if scaling up the model size can…
Frontier LLMs like ChatGPT are powerful but vulnerable to attack. Scale helps with many things, so we wanted to see if scaling up the model size can…
Liked by Adam Gleave
-
Our paper “Debating with More Persuasive LLMs Leads to More Truthful Answers” was awarded best paper at ICML! This is one of the first AI safety…
Our paper “Debating with More Persuasive LLMs Leads to More Truthful Answers” was awarded best paper at ICML! This is one of the first AI safety…
Liked by Adam Gleave
-
💗🗣 How does translating the Korean word "jeong" (정) illustrate the challenge of AI alignment? 🤖🎯 Been Kim discusses alignment and…
💗🗣 How does translating the Korean word "jeong" (정) illustrate the challenge of AI alignment? 🤖🎯 Been Kim discusses alignment and…
Liked by Adam Gleave
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Adam Gleave
-
Adam Gleave
-
Adam Gleave
-
Adam Gleave
Deputy Sheriff at Davidson County Sheriff's Ofc
-
adam gleave
Construction Laborer at american excavating
5 others named Adam Gleave are on LinkedIn
See others named Adam Gleave