Prof in CS/NLP at IT University of Copenhagen
garak guy, garak.ai
"berømt skikkelse"
"like a gazelle"
Copenhagen/Seattle
"What does it mean for agentic AI to preserve privacy?" - Niloofar Mireshghallah, Meta/CMU
(Friday 1st Aug, 11.00; Austria Center Vienna Hall B)
See you there!
#acl2025 #acl2025nlp
"What does it mean for agentic AI to preserve privacy?" - Niloofar Mireshghallah, Meta/CMU
(Friday 1st Aug, 11.00; Austria Center Vienna Hall B)
See you there!
#acl2025 #acl2025nlp
* Audio attacks, for multimodal models
* More training data membership inference attacks
* Multilingual attacks can now also use GCP
* Detailed eval summary in one JSONL row/object
+more :)
details: github.com/NVIDIA/garak...
* Audio attacks, for multimodal models
* More training data membership inference attacks
* Multilingual attacks can now also use GCP
* Detailed eval summary in one JSONL row/object
+more :)
details: github.com/NVIDIA/garak...
Key takeaway: the product doesn’t suffer, but the process does. And when it comes to essays, the process *is* how they learn.
arxiv.org/pdf/2506.088...
she's a serious professor
we went through to the room, opened the balcony door, and buried a bottle of champagne in the metre of snow
good times
she's a serious professor
we went through to the room, opened the balcony door, and buried a bottle of champagne in the metre of snow
good times
www.instagram.com/reel/DKz9ezj...
www.instagram.com/reel/DKz9ezj...
"wirk smorter nat horder"
accents dreamed up by the utterly deranged
(what is going on with that 🇺🇸 vowel sheft)
"wirk smorter nat horder"
accents dreamed up by the utterly deranged
(what is going on with that 🇺🇸 vowel sheft)
- Advice for female agents in WW2, provided during SOE training
- Advice for female agents in WW2, provided during SOE training
make it stop
make it stop
* successfully not reading any news
* getting to do 50h of work in one week (it was enjoyable, usual caveats apply)
* finally a largely healthy family
* successfully not reading any news
* getting to do 50h of work in one week (it was enjoyable, usual caveats apply)
* finally a largely healthy family
On 11.2 you can see me at:
* AI Assurance and Testing: Global Perspectives
* Building trustworthy AI: balancing innovation, responsibility, and democratization
On 11.2 you can see me at:
* AI Assurance and Testing: Global Perspectives
* Building trustworthy AI: balancing innovation, responsibility, and democratization