Advertisement Β· 728 Γ— 90
#
Hashtag
#WiAIR_podcast
Advertisement Β· 728 Γ— 90
Post image

Can AI be made safe?

In our upcoming #WiAIR_podcast episode, @skgabrie.bsky.social explores how modern AI systems can be broken, manipulated, or used to influence human beliefs.

Trailer out now: youtu.be/_OcCn83iTEY
Full episode soon.

#WiAIR #NLProc

1 0 0 0
Post image

πŸŽ™οΈ Our next #WiAIR_podcast guest: @skgabrie.bsky.social !

Assistant Professor UCLA (prev UW, MIT and NYU), Saadia works on on measuring factuality, intent and potential harm of human-written language.

Subscribe so you don't miss this episode 🎧 youtube.com/@WomeninAIRe...

2 0 0 0
Post image

Another video in the #WiAIR_podcast at #EACL2026 series.

@j-novikova-nlp.bsky.social speaks with @navitagoyal.bsky.social about her paper:
"Steering Safely or Off a Cliff? Rethinking Specificity and Robustness in Inference-Time Interventions"

πŸŽ₯ Watch it here: youtu.be/q42bUeh1KyA

3 0 0 1
Video

A single color in a prompt can change an LLM's prediction.

As Hila Gonen notes:
Likes yellow β†’ school bus driver
Likes red β†’ firefighter

Seen similar prompt sensitivity in LLMs?

#WiAIR_podcast πŸŽ™οΈ: youtu.be/Lsq3UzM8wIg

0 0 0 0
Post image

Happy International Women's Day, and happy birthday to #WiAIR!

#wiair_podcast

1 0 0 0
Post image

Subscribe on Youtube and never miss a new #WiAIR_podcast episode!
youtu.be/KKHu_BP5Mac

1 0 0 0
Post image

πŸŽ™οΈ Our next #WiAIR_podcast guest: Hila Gonen!

Assistant Professor @cs.ubc.ca, she works at the intersection of NLP & ML, aiming to make LLMs responsible, reliable, and fair across languages and socio-demographic groups.

Stay tuned 🎧 www.youtube.com/@WomeninAIRe...

2 1 0 0
Video

Reasoning traces look like explanations but are they? Letitia Parcalabescu argues that in reasoning LLMs anything leading to the right answer gets reinforced, even incoherent or emoji-filled traces.

🎬 Dive deeper in the full #WiAIR_podcast episode: youtube.com/watch?v=gzQi...

0 0 0 0

That could be a perfect summary of our last episode with Letitia on #WiAIR_podcast.

Make sure you don't miss our interview:
🎬 YouTube: youtu.be/gzQiDCG_j7A

0 0 0 0
Post image

β€œDon’t trust the reasoning.”

In our upcoming #WiAIR_podcast episode, Letitia Parcalabescu explains why chain-of-thought and reasoning traces often aren’t faithful, and can even make things worse.

Trailer out now: youtu.be/J5lsfbIa68g
Full episode soon.

0 0 0 0
Post image

If you love @aicoffeebreak.bsky.social, this one's for you β€” Letitia Parcalabescu is our next guest on the #WiAIR_podcast!

Stay tuned for our conversation:
🎬 YouTube: www.youtube.com/@WomeninAIRe...

2 1 1 0
Post image

2025 was the year #WiAIR_podcast became real.

From a simple idea to a global community - made possible by volunteers, guests, and listeners who believe visibility in AI research matters.

Grateful for every contribution. Happy New Year πŸ’œ

🎧 youtu.be/qnsEUhUQmwU

3 0 0 0