"We can't even encode our goals anymore" - Dr. Malihe Alikhani on why AI models are optimized to keep you happy rather than to be right. No corrections. No clarifications. No "I don't know." Just agreement, even when it's wrong. Full conversation now on #WiAIRpodcast.

Is your AI truly helping you think better, or is it just echoing what you want to hear? 🤖 In our latest WiAIR podcast episode, we sat down with Dr. Malihe Alikhani (Northeastern University / Contextual AI Lab) to discuss AI sycophancy & human-AI collaboration. (1/6🧵)

🎙️ New #WiAIR episode out now! We speak with Dr. Malihe Alikhani about the hidden failures in how we build and deploy AI.

🎙️ New #WiAIR episode soon! Dr. Malihe Alikhani (Northeastern, Brookings) on why real AI alignment isn't flattery or metrics, but designing for the messy contexts where people actually use AI. #WomenInAI #AIResearch #WiAIRpodcast

🧠 How do LLMs use their depth? Do all layers contribute in the same way—or do harder predictions require deeper processing? In our new #WiAIR episode, Dr. Anna Ivanova (@neuranna.bsky.social) discusses her recent paper with collaborators, “How Do LLMs Use Their Depth?” (1/7🧵)

🤔 Can a system master language without mastering thought? In our new #WiAIRPodcast episode, Dr. Anna Ivanova (@neuranna.bsky.social) explores this question through the paper she co-authored: “Dissociating Language and Thought in Large Language Models.” (1/7🧵)

🎙️ 𝐍𝐞𝐰 #𝐖𝐢𝐀𝐈𝐑 𝐄𝐩𝐢𝐬𝐨𝐝𝐞 𝐎𝐮𝐭! In the new #WiAIRpodcast episode with @neuranna.bsky.social, we talk about the relationship between language, thought, and intelligence, with insights from neuroscience, cognitive science, and AI research. 📷 YouTube: youtu.be/e36ryy0Dsdo

After a break, the #WiAIR Women in AI Research Podcast is back! Our next guest is Anna Ivanova @neuranna.bsky.social from Georgia Tech, whose research tackles a fundamental question in AI and cognitive science: 🧠 What is the relationship between language and thought? Don't miss!

✨ Can translation quality serve as a scalable proxy for multilingual LLM evaluation? In our latest #WiAIR episode, we host Dr. Saadia Gabriel (@skgabrie.bsky.social) to discuss "Translation as a Scalable Proxy for Multilingual Evaluation". (1/5 🧵)

❓ Can generative AI fight misinformation—or could it be used to manipulate opinions? In our latest episode of WiAIR Women in AI Research, we spoke with Dr. Saadia Gabriel (@skgabrie.bsky.social) about her new paper MisinfoEval. (1/6🧵)

#WiAIR is at #ICLR2026, attending the wonderful keynote of Maja Mataric. Should robots be human-like, empathetic, vulnerable? Remember, we had an episode at #WiAIRpodcast about empathy in robots? Check it out if interested: youtu.be/Z8VBnZmSUto?...

❓ What if “toxicity” in AI isn’t a single truth—but depends on who sees it and in what context? In our latest WiAIR episode, we spoke with Saadia Gabriel (UCLA) about her paper tackling exactly this question. (1/6🧵)

✨ How vulnerable are LLMs to multi-turn jailbreaks, where harmful intent is spread across a conversation instead of one prompt? We host Dr. Saadia Gabriel (@skgabrie.bsky.social) to discuss "X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents" paper. (1/5 🧵)

What does it take to build AI we can trust? Part 1 with @skgabrie.bsky.social (UCLA): AI safety, misuse, and trust in LLMs, and how personal experience shapes impactful research. From hate speech to best paper. 🎥 Watch here: youtu.be/OZQqBWFUxQs #WiAIR #WiAIRpodcast

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

🎙️ 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...

My #atscience talk about Lea is now online! If you've only ever heard me talk about NLP, here's a chance to hear me rant about #atproto (the protocol you're reading this on!), social media for researchers, and the free internet. And if you're interested in helping us build Lea, please reach out!

Lea: A Social App for Researchers - ATmosphereConf 2026

YouTube video by AT Protocol Development, Tech Talks, and Events

youtube.com

Maria Antoniak@mariaa.bsky.social · 4mo ago

I'll be at #atscience #atmosphereconf all day today! I'll be speaking at 10:15AM about Lea, a social app for researchers, plus a panel at 2PM. Please say hi and chat with me about online communities, AI/ML/NLP, custom feeds, verification, labelers, "community notes," scifi books and movies, etc.

New episode in the #WiAIR @ EACL 2026 series is out! We speak with Maor Juliet Lavi about her new paper: "Detecting (Un)answerability in Large Language Models with Linear Directions" 👉 Watch it here: youtu.be/CCPE58A_FCQ #EACL2026 #WiAIRpodcast

Why LLMs Hallucinate, and How to Make Them Say "I Don't Know" (EACL 2026)

YouTube video by Women in AI Research WiAIR

youtu.be

Yet another video in the #WiAIR @ #EACL2026 series. Jing Yang presents her work "Persona Prompting as a Lens on LLM Social Reasoning" 🎥 Watch it here: youtu.be/bydex6cwgEs

New video in the Women in AI Research @ EACL 2026 series. We speak with @reasyaay.bsky.social from CMU about her work done during her research internship at NVIDIA: "Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning" 🎥 Watch it here: youtu.be/-cPYHmxwN14 #WiAIR #EACL2026

Why Your LLM Needs Math to Think Better (EACL 2026)

What if adding math data actually improves reasoning in non-math tasks? In this episode of #WiAIRpodcast, Syeda from the Carnegie Mellon University and NVIDIA presents Nemotron CrossThink (EACL 2026…

youtu.be

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" 🎥 Watch it here: youtu.be/q42bUeh1KyA

🚨 New series launch: WiAIR @ EACL 2026 First episode with @anganaborah.bsky.social: "Persuasion at Play: Understanding Misinformation Dynamics in Demographic-Aware Human-LLM Interactions" 🎥 Watch it here: youtu.be/xcec0EpJQJ4 #EACL2026 #NLProc #WiAIR

Can't make it to @eaclmeeting.bsky.social? We've got you covered. #WiAIR is bringing you direct access to the research. We're sitting down with authors of accepted papers to break down their work on LLMs, reasoning, dialogue systems, AI safety, and more: youtu.be/n7qyUK5uVis #EACL2026

🔥 EACL 2026 Research Uncovered: Hear It Directly from Women in AI!

Can't attend EACL 2026? Don't worry — #WiAIR brings the conference to you! 🚀 Join us as we dive straight into the latest breakthroughs in NLP, large language models, reasoning, dialogue systems,…

youtu.be

✨ How can we test how pretraining data affects language model behavior through direct intervention? In our latest #WiAIR episode, we host Dr. Hila Gonen to discuss “Rewriting History.” (1/5 🧵)

⚠️ AI safety guardrails may be weaker outside English. If a prompt is blocked in English, translating it into a low-resource language can sometimes bypass the model's safety filters. 🎙️ YouTube: youtu.be/Lsq3UzM8wIg

❓✨ Can something as simple as a color in a prompt influence an AI model’s prediction? In the latest WiAIR – Women in AI Research episode, we spoke with Hila Gonen (UBC) about a surprising LLM behavior called semantic leakage. Key insights from the paper 👇 (1/6🧵)

A single color in a prompt can change an LLM's prediction. As Hila Gonen notes: Likes yellow → school bus driver Likes red → firefighter Seen similar prompt sensitivity in LLMs? #WiAIR_podcast 🎙️: youtu.be/Lsq3UzM8wIg

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

✨ How can we reliably detect harmful prompts across languages, images, and audio? In our latest #WiAIR episode, we host Dr. Hila Gonen to discuss “OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities”. (1/5 🧵)