Colin Shea-Blymyer

So excited to share that today @CSETGeorgetown and @emergingtechobs are launching an ✨updated✨ version of our chip supply chain explorer! We've got: 👉 New data 👉 New features 👉 New analysis Links in thread

Why does #ArtificialIntelligence red-teaming suck? How can we make it suck less? All this and more at the next CSET webinar: cset.georgetown.edu/event/whats-ne… Join us for an awesome conversation.

What: CSET Webinar 📺 When: Tuesday, 3/25 at 12PM ET 📅 What’s next for AI red-teaming? And how do we make it more useful? Join @CLiaghati, @tori_westerhoff, @MariusHobbhahn, and CSET's @SheaBly & Jessica Ji for a great discussion (link in comments).

✨🏛️New interactive tool🏛️✨ Use the latest @emergingtechobs resource to track AI governance from D.C. to Beijing. ETO AGORA is a living collection of AI-relevant laws, regulations, standards, and other governance documents from the U.S. and around the world 🌎

@Temujinsrule @UniofOxford @AIESConf I started by studying computer science and nurturing a healthy interest in philosophy. I have colleagues that that did the opposite! Many people I work with started as SEs/MLEs and got involved with their org's responsible AI policies. Stay curious!

@SheaBly @UniofOxford @AIESConf Hey Colin, how can somebody start with creating a career in ai ethics?

Last week I presented my research on auditing the ethics of AI systems at @UniofOxford for the @AIESConf - a dream come true!

Workshop Announcement 📯 On Dec 4 (1 day after AISIC Plenary) @CSETGeorgetown is hosting a workshop on the future of AI testing. Workshop will run from 9am-1pm on Georgetown's Capitol Campus. If you have experience testing AI systems please reach out to me for more details!

ICYMI: Last week, the White House released its first-ever National Security Memo on AI. Our experts broke down what it means for U.S. national security and AI development. cset.georgetown.edu/article/the-na…

Earlier today, the White House released its first-ever National Security Memo on AI. Our experts tackled seven pressing questions about the memo and what it means for U.S. national security & AI development. cset.georgetown.edu/article/the-na…

Paper link: arxiv.org/abs/2408.00147

I'll be presenting work on logic, ethics, and agency at @AIESConf - I'm also down to chat about AI red-teaming, safety and security!

AI models at the world’s largest hacking convention! @SheaBly's new blog post describes the lessons he learned from winning @aivillage_dc’s AI red-teaming challenge. cset.georgetown.edu/article/how-i-…

How is state-of-the-art #AI red-teaming being done in practice? Our new blog post by CSET's @SheaBly and Jessica Ji summarizes findings from this year’s @defcon and lays out a research agenda for future work on this important topic 👀⬇️ cset.georgetown.edu/article/revisi…

Want to know how I won @aivillage_dc's AI hacking competition? Find out in my first blog post for @CSETGeorgetown!

New piece out with my colleague Zach Arnold, laying out some basic common-sense policies that people with a wide range of views on AI could get behind: -Building govt capacity -Better measurement -Independent auditing -Disclosure -Incident tracking -Liability 🧵:

@SheaBly made the most interesting submission and got an extra $1k. Dustin Farley had the best body of work and also got an extra $1k.

Congratulations to the top four teams winning prizes in our Water challenge! Our winning teams were from @EngineeringOSU, @WSUPullman, @ucmerced, and a combo @virginia_tech and @UVA team. The challenge video,youtu.be/OJjgRfNa7Hk, gives a sense of what they hacked!#AgAth0n2023

@StarfieldGame listening to Todd on Lex Fridman has me reciting poetry: genius.com/Ray-bradbury-i…

@SomeMoreNews the boars are at it again! Why did they steal shakira's bag? I need answers! BBC News - Shakira: Singer attacked by a pair of wild boars bbc.co.uk/news/world-eur…

If you are in a slack channel with 200 other people, and you're responding to someone, please make a thread... please...