BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//AI Safety Tübingen - ECPv6.15.17.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://aisafetytuebingen.com
X-WR-CALDESC:Events for AI Safety Tübingen
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20251026T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20270328T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20271031T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Berlin:20260521T180000
DTEND;TZID=Europe/Berlin:20260521T193000
DTSTAMP:20260605T035055
CREATED:20260521T140233Z
LAST-MODIFIED:20260521T140233Z
UID:2640-1779386400-1779391800@aisafetytuebingen.com
SUMMARY:MATS Q&A
DESCRIPTION:We are hosting a Q&A about the MATS fellowship with current and previous fellows. We’ll cover what it’s like to do research at MATS\, give some advice for the application process\, and try to answer all your questions about the program. \nYou can find more information here: https://www.matsprogram.org/program/autumn-2026 \nAs usual\, we’ll provide dinner and drinks.
URL:https://aisafetytuebingen.com/event/mats-qa/
LOCATION:MvL1\, Maria-von-Linden Straße 1\, Tübingen
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Berlin:20260511T180000
DTEND;TZID=Europe/Berlin:20260511T200000
DTSTAMP:20260605T035055
CREATED:20260502T152908Z
LAST-MODIFIED:20260502T152908Z
UID:2586-1778522400-1778529600@aisafetytuebingen.com
SUMMARY:Alexander Panfilov: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
DESCRIPTION:Alexander Panfilov (Sasha) will present his recent work on automating the discovery of adversarial attack algorithms for LLMs (https://arxiv.org/abs/2603.24511). This paper has gotten quite a bit of attention\, as the results are an early demonstration that incremental safety and security research can be automated using LLM agents. We are happy to host Sasha for a talk and Q&A. As usual\, we’ll provide dinner and drinks. Everybody is welcome to join!
URL:https://aisafetytuebingen.com/event/alexander-panfilov-autoresearch-discovers-state-of-the-art-adversarial-attack-algorithms-for-llms/
LOCATION:MvL1\, Maria-von-Linden Straße 1\, Tübingen
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Berlin:20260504T180000
DTEND;TZID=Europe/Berlin:20260504T193000
DTSTAMP:20260605T035055
CREATED:20260502T150845Z
LAST-MODIFIED:20260502T150845Z
UID:2579-1777917600-1777923000@aisafetytuebingen.com
SUMMARY:AI Calibration Game
DESCRIPTION:Test your knowledge of AI facts while practicing calibrated uncertainty\, in a fun estimation game by Markus Anderljung (https://www.markusanderljung.com/ai-calibration-game.html). We will split into small groups\, and compete for the highest score. \nEverybody is welcome to join! Since many of you will be busy with NeurIPS submissions this week\, we are aiming to keep this meetup more relaxed and shorter than usual. We’ll pre-order Pizza\, so that it arrives at 6pm already. \n  \n 
URL:https://aisafetytuebingen.com/event/ai-calibration-game/
LOCATION:MvL1\, Maria-von-Linden Straße 1\, Tübingen
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Berlin:20260427T180000
DTEND;TZID=Europe/Berlin:20260427T200000
DTSTAMP:20260605T035055
CREATED:20260427T105219Z
LAST-MODIFIED:20260427T105219Z
UID:2562-1777312800-1777320000@aisafetytuebingen.com
SUMMARY:Claude Mythos discussion
DESCRIPTION:Johannes will give a short overview of results from the Mythos Preview System Card\, and then the main focus of the meeting will be on discussion: Does this change how models will be released from now on? What are the safety and security implications? Should this update us on timelines or specific threat models? \nIf you haven’t seen it\, you can read up on Claude Mythos here:\n•⁠ ⁠Project Glasswing announcement [https://www.anthropic.com/glasswing]\n•⁠ ⁠System Card: Claude Mythos Preview [https://cdn.sanity.io/files/4zrzovbb/website/7624816413e9b4d2e3ba620c5a5e091b98b190a5.pdf]\n•⁠ ⁠Video Summary by 80k Hours [https://www.youtube.com/watch?v=Tjw9K9mQp4I]
URL:https://aisafetytuebingen.com/event/claude-mythos-discussion/
LOCATION:MvL1\, Maria-von-Linden Straße 1\, Tübingen
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Berlin:20260413T180000
DTEND;TZID=Europe/Berlin:20260413T200000
DTSTAMP:20260605T035055
CREATED:20260409T125649Z
LAST-MODIFIED:20260409T125649Z
UID:2483-1776103200-1776110400@aisafetytuebingen.com
SUMMARY:[Talk + Q&A] Compute Governance with Yannick Mühlhäuser (FLI)
DESCRIPTION:Yannick Mühlhäuser is working as a Policy Researcher at the Future of Life Institute and as Research Manager at ERA Cambridge. Previously\, he was a Talos Fellow in Brussels and studied Physics in Tübingen. Yannick will briefly give an overview of his work on hardware-enabled governance and AI verification\, followed by an open Q&A. Since Yannick has a technical background and insights into the policy sphere\, we hope the event will be of interest to both the technical and non-technical people in this group.
URL:https://aisafetytuebingen.com/event/talk-qa-compute-governance-with-yannick-muhlhauser-fli/
LOCATION:MvL1\, Maria-von-Linden Straße 1\, Tübingen
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Berlin:20260323T180000
DTEND;TZID=Europe/Berlin:20260323T200000
DTSTAMP:20260605T035055
CREATED:20260317T195727Z
LAST-MODIFIED:20260317T195727Z
UID:2378-1774288800-1774296000@aisafetytuebingen.com
SUMMARY:[Paper Discussion] The Artificial Self: Characterising the landscape of AI identity
DESCRIPTION:We will discuss the paper The Artificial Self: Characterising the landscape of AI identity by Douglas et al. (2026).
URL:https://aisafetytuebingen.com/event/paper-discussion-the-artificial-self-characterising-the-landscape-of-ai-identity/
CATEGORIES:Reading Group
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Berlin:20260318T080000
DTEND;TZID=Europe/Berlin:20260318T170000
DTSTAMP:20260605T035055
CREATED:20260318T073334Z
LAST-MODIFIED:20260318T073334Z
UID:2382-1773820800-1773853200@aisafetytuebingen.com
SUMMARY:[Paper Discussion] Legal Alignment for Safe and Ethical AI
DESCRIPTION:We will discuss the paper Legal Alignment for Safe and Ethical AI by Kolt et al. (2026).
URL:https://aisafetytuebingen.com/event/paper-discussion-legal-alignment-for-safe-and-ethical-ai/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Berlin:20260316T180000
DTEND;TZID=Europe/Berlin:20260316T200000
DTSTAMP:20260605T035055
CREATED:20260315T130611Z
LAST-MODIFIED:20260315T130611Z
UID:2366-1773684000-1773691200@aisafetytuebingen.com
SUMMARY:[Talk] by Daniel Tan\, presenting his work
DESCRIPTION:Daniel Tan is one of the main authors of the Emergent Misalignment paper and also the main author of a paper introducing Inoculation Prompting. In many of our discussions so far\, we have talked about these papers\, so this could be a very interesting event for many of you!
URL:https://aisafetytuebingen.com/event/talk-by-daniel-tan-presenting-his-work/
LOCATION:MvL1\, Maria-von-Linden Straße 1\, Tübingen
CATEGORIES:Reading Group
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Berlin:20260309T180000
DTEND;TZID=Europe/Berlin:20260309T200000
DTSTAMP:20260605T035055
CREATED:20260308T102105Z
LAST-MODIFIED:20260308T102523Z
UID:2266-1773079200-1773086400@aisafetytuebingen.com
SUMMARY:[Paper Discussion] Who's in charge? Disempowerment Patterns in Real-World LLM Usage
DESCRIPTION:We will discuss this recent paper which is related to the “Gradual Disempowerment” paper from about a year ago: https://gradual-disempowerment.ai/ \nThere is also an interesting podcast interview with one of the authors.
URL:https://aisafetytuebingen.com/event/paper-discussion-whos-in-charge-disempowerment-patterns-in-real-world-llm-usage/
LOCATION:MvL1\, Maria-von-Linden Straße 1\, Tübingen
CATEGORIES:Reading Group
ATTACH;FMTTYPE=image/png:https://aisafetytuebingen.com/wp-content/uploads/2026/03/Screenshot-2026-03-08-at-11.17.25.png
END:VEVENT
END:VCALENDAR