Sílvia Casacuberta
@sicapu.bsky.social
Computer Science PhD student & Knight-Hennessy scholar at @stanford.edu.
Prev.: @ox.ac.uk with @rhodeshouse.ox.ac.uk, @harvard.edu '23, @maxplanck.de, @ethz.ch, IBM Research.
Theory CS for Trustworthy AI
https://silviacasacuberta.com
Prev.: @ox.ac.uk with @rhodeshouse.ox.ac.uk, @harvard.edu '23, @maxplanck.de, @ethz.ch, IBM Research.
Theory CS for Trustworthy AI
https://silviacasacuberta.com
Reposted by Sílvia Casacuberta
If you swap each letter in “bomb” with the next letter in the alphabet, you’ll get “cpnc.” Recently, scientists showed that and other methods can bypass filters on LLMs like Gemini, DeepSeek and Grok. @peterha2l.bsky.social reports: www.quantamagazine.org/cryptographe...
Cryptographers Show That AI Protections Will Always Have Holes | Quanta Magazine
Large language models such as ChatGPT come with filters to keep certain info from getting out. A new mathematical argument shows that systems like this can never be completely safe.
www.quantamagazine.org
December 10, 2025 at 3:42 PM
If you swap each letter in “bomb” with the next letter in the alphabet, you’ll get “cpnc.” Recently, scientists showed that and other methods can bypass filters on LLMs like Gemini, DeepSeek and Grok. @peterha2l.bsky.social reports: www.quantamagazine.org/cryptographe...
Reposted by Sílvia Casacuberta
The pre-recorded videos (for the talks whose authors opted in to submit one) are now available on our YouTube channel: m.youtube.com/@FOCS2025
They're also linked from the main website's schedule!
They're also linked from the main website's schedule!
FOCS 2025
Videos from the 66th IEEE Symposium on Foundations of Computer Science (FOCS) 2025
m.youtube.com
December 9, 2025 at 4:40 AM
The pre-recorded videos (for the talks whose authors opted in to submit one) are now available on our YouTube channel: m.youtube.com/@FOCS2025
They're also linked from the main website's schedule!
They're also linked from the main website's schedule!
Reposted by Sílvia Casacuberta
The researchers Lijie Chen (left), Igor Oliveira (top-right) and Jitau Li recently used “reverse mathematics” to connect a theorem called the pigeonhole principle to a whole class of complexity problems. www.quantamagazine.org/reverse-math...
December 6, 2025 at 9:04 PM
The researchers Lijie Chen (left), Igor Oliveira (top-right) and Jitau Li recently used “reverse mathematics” to connect a theorem called the pigeonhole principle to a whole class of complexity problems. www.quantamagazine.org/reverse-math...
Reposted by Sílvia Casacuberta
Reminder that this is today at 7 pm! Please join us if you are at #NeurIPS2025
At #NeurIPS2025? Join us for a Social on Wednesday at 7 PM, featuring a fireside chat with Jon Kleinberg and mentoring tables.
Ft. mentors @djfoster.bsky.social @surbhigoel.bsky.social @aifi.bsky.social @gautamkamath.com and more!
Ft. mentors @djfoster.bsky.social @surbhigoel.bsky.social @aifi.bsky.social @gautamkamath.com and more!
December 3, 2025 at 10:31 PM
Reminder that this is today at 7 pm! Please join us if you are at #NeurIPS2025
Hello Bluesky! Joining the app in time to say that I’ll be attending NeurIPS this week! I will be presenting our paper (joint work with Varun Kanade) on building predictors that abstain optimally and fairly.
neurips.cc/virtual/2025...
neurips.cc/virtual/2025...
December 4, 2025 at 1:07 AM
Hello Bluesky! Joining the app in time to say that I’ll be attending NeurIPS this week! I will be presenting our paper (joint work with Varun Kanade) on building predictors that abstain optimally and fairly.
neurips.cc/virtual/2025...
neurips.cc/virtual/2025...