Maksym Andriushchenko
@maksym-andr.bsky.social
Faculty at the ELLIS Institute Tübingen and Max Planck Institute for Intelligent Systems. Leading the AI Safety and Alignment group. PhD from EPFL supported by Google & OpenPhil PhD fellowships.
More details: https://www.andriushchenko.me/
More details: https://www.andriushchenko.me/
📣 Incredibly excited to participate in writing the International AI Safety Report, chaired by Yoshua Bengio, as chapter lead for the capabilities chapter!
⚖️ AI is progressing so rapidly that yearly updates are no longer sufficient.
1/3
⚖️ AI is progressing so rapidly that yearly updates are no longer sufficient.
1/3
AI is evolving too quickly for an annual report to suffice. To help policymakers keep pace, we're introducing the first Key Update to the International AI Safety Report. 🧵⬇️
(1/10)
(1/10)
October 15, 2025 at 12:24 PM
📣 Incredibly excited to participate in writing the International AI Safety Report, chaired by Yoshua Bengio, as chapter lead for the capabilities chapter!
⚖️ AI is progressing so rapidly that yearly updates are no longer sufficient.
1/3
⚖️ AI is progressing so rapidly that yearly updates are no longer sufficient.
1/3
Reposted by Maksym Andriushchenko
A new recording of our FridayTalks@Tübingen series is online!
AI Safety and Alignment
by
@maksym-andr.bsky.social
Watch here: youtu.be/7WRW8MDQ8bk
AI Safety and Alignment
by
@maksym-andr.bsky.social
Watch here: youtu.be/7WRW8MDQ8bk
AI Safety and Alignment - [Maksym Andriushchenko]
YouTube video by Friday Talks Tübingen
youtu.be
September 11, 2025 at 1:18 PM
A new recording of our FridayTalks@Tübingen series is online!
AI Safety and Alignment
by
@maksym-andr.bsky.social
Watch here: youtu.be/7WRW8MDQ8bk
AI Safety and Alignment
by
@maksym-andr.bsky.social
Watch here: youtu.be/7WRW8MDQ8bk
🚨 Incredibly excited to share that I'm starting my research group focusing on AI safety and alignment at the ELLIS Institute Tübingen and Max Planck Institute for Intelligent Systems in September 2025! 🚨
1/n
1/n
August 6, 2025 at 3:43 PM
🚨 Incredibly excited to share that I'm starting my research group focusing on AI safety and alignment at the ELLIS Institute Tübingen and Max Planck Institute for Intelligent Systems in September 2025! 🚨
1/n
1/n
🚨Excited to release OS-Harm! 🚨
The safety of computer use agents has been largely overlooked.
We created a new safety benchmark based on OSWorld for measuring 3 broad categories of harm:
1. deliberate user misuse,
2. prompt injections,
3. model misbehavior.
The safety of computer use agents has been largely overlooked.
We created a new safety benchmark based on OSWorld for measuring 3 broad categories of harm:
1. deliberate user misuse,
2. prompt injections,
3. model misbehavior.
June 19, 2025 at 3:28 PM
🚨Excited to release OS-Harm! 🚨
The safety of computer use agents has been largely overlooked.
We created a new safety benchmark based on OSWorld for measuring 3 broad categories of harm:
1. deliberate user misuse,
2. prompt injections,
3. model misbehavior.
The safety of computer use agents has been largely overlooked.
We created a new safety benchmark based on OSWorld for measuring 3 broad categories of harm:
1. deliberate user misuse,
2. prompt injections,
3. model misbehavior.
🚨Excited to share our new work!
1. Not only GPT-4 but also other frontier LLMs have memorized the same set of NYT articles from the lawsuit.
2. Very large models, particularly with >100B parameters, have memorized significantly more.
🧵1/n
1. Not only GPT-4 but also other frontier LLMs have memorized the same set of NYT articles from the lawsuit.
2. Very large models, particularly with >100B parameters, have memorized significantly more.
🧵1/n
December 9, 2024 at 10:01 PM
🚨Excited to share our new work!
1. Not only GPT-4 but also other frontier LLMs have memorized the same set of NYT articles from the lawsuit.
2. Very large models, particularly with >100B parameters, have memorized significantly more.
🧵1/n
1. Not only GPT-4 but also other frontier LLMs have memorized the same set of NYT articles from the lawsuit.
2. Very large models, particularly with >100B parameters, have memorized significantly more.
🧵1/n
📢 I'll be at NeurIPS 🇨🇦 from Tuesday to Sunday!
Let me know if you're also coming and want to meet. Would love to discuss anything related to AI safety/generalization.
Also, I'm on the academic job market, so would be happy to discuss that as well! My application package: andriushchenko.me.
🧵1/4
Let me know if you're also coming and want to meet. Would love to discuss anything related to AI safety/generalization.
Also, I'm on the academic job market, so would be happy to discuss that as well! My application package: andriushchenko.me.
🧵1/4
Maksym Andriushchenko
I'm a PhD student in computer science at EPFL advised by Nicolas Flammarion. I'm interested in understanding why machine learning works and why it fails.
andriushchenko.me
December 7, 2024 at 7:26 PM
📢 I'll be at NeurIPS 🇨🇦 from Tuesday to Sunday!
Let me know if you're also coming and want to meet. Would love to discuss anything related to AI safety/generalization.
Also, I'm on the academic job market, so would be happy to discuss that as well! My application package: andriushchenko.me.
🧵1/4
Let me know if you're also coming and want to meet. Would love to discuss anything related to AI safety/generalization.
Also, I'm on the academic job market, so would be happy to discuss that as well! My application package: andriushchenko.me.
🧵1/4
Reposted by Maksym Andriushchenko
Mindblowing: EPFL PhD student @maksym-andr.bsky.social, winner of best CS thesis award, showed that leading hashtag#AI models are not robust to simple adaptive jailbreaking attacks. Indeed, he managed to jailbraik all models with a 100% success rate 🤯
Jailbraking paper: arxiv.org/abs/2404.02151
Jailbraking paper: arxiv.org/abs/2404.02151
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
We show that even the most recent safety-aligned LLMs are not robust to simple adaptive jailbreaking attacks. First, we demonstrate how to successfully leverage access to logprobs for jailbreaking: we...
lnkd.in
December 6, 2024 at 7:00 AM
Mindblowing: EPFL PhD student @maksym-andr.bsky.social, winner of best CS thesis award, showed that leading hashtag#AI models are not robust to simple adaptive jailbreaking attacks. Indeed, he managed to jailbraik all models with a 100% success rate 🤯
Jailbraking paper: arxiv.org/abs/2404.02151
Jailbraking paper: arxiv.org/abs/2404.02151
really feels like Twitter circa 2018. good old days... 😀
November 20, 2024 at 10:47 AM
really feels like Twitter circa 2018. good old days... 😀