Sören Mindermann
@sorenmind
Followers
1K
Following
2K
Statuses
596
Postdoc with Yoshua Bengio, Mila
Oxford
Joined May 2016
Super excited to share that **Inferring the effectiveness of government interventions against COVID-19** was just published in Science !! Work done with amazing collaborators @JanMBrauner, @MrinankSharma ... 1/
11
61
191
RT @mmitchell_ai: New piece out! We explain why Fully Autonomous Agents Should Not be Developed, breaking “AI Agent” down into its componen…
0
137
0
RT @Yoshua_Bengio: Analyzing the ethics and risks of autonomous agents is crucial. Thank you for your insightful work @mmitchell_ai, @eviji…
0
26
0
RT @dwarkesh_sp: Thanks to @EgeErdil2, @tamaybes, and @g_leech_ for collaborating with me in developing these ideas.
0
18
0
RT @random_walker: I appreciate that the authors of the report solicited and incorporated feedback from experts with a diverse range of vie…
0
10
0
Thank you for the shout out Deb - it's been productive+fun to work with you on this!
The International AI Safety report went through many rounds of feedback, from an increasingly diverse coalition of scholars from all over the world. Very happy with how responsive this team, and esp @Yoshua_Bengio have been - hopefully this informs more common sense AI policy!
0
0
1
RT @rajiinio: The International AI Safety report went through many rounds of feedback, from an increasingly diverse coalition of scholars f…
0
18
0
RT @Yoshua_Bengio: Since the end of the writing period for the Report, data on two new models – o3 & R1 – has suggested that advances in ca…
0
16
0
RT @geoffreyirving: I'm excited that the International AI Safety Report is out! It is important that the capabilities, risks, and mitigatio…
0
5
0
RT @hugo_larochelle: So proud to see the leadership of @Yoshua_Bengio and @Mila_Quebec in producing this deeply researched report, resultin…
0
6
0
RT @Yoshua_Bengio: Today, we are publishing the first-ever International AI Safety Report, backed by 30 countries and the OECD, UN, and EU.…
0
533
0
I think this is an important project to continue. To fully realize AI's potential, we need to understand and manage its risks. This scientific assessment aims to help policymakers design targeted interventions that address risks while promoting benefits.
0
0
5
@Simeon_Cps Batch normalization can create some dependencies between different data in a batch but during training
1
0
2
RT @OwainEvans_UK: New paper: We train LLMs on a particular behavior, e.g. always choosing risky options in economic decisions. They can *d…
0
140
0
RT @_achan96_: Whether 2025/6/7/8/etc is the year of AI agents, we will need tools to help us unlock their benefits and manage their risks.…
0
32
0
Would be curious for a more LLM-friendly benchmark similar to ARC-AGI but harder @mikeknoop @fchollet.
0
0
1