Orpheus Lummis
@orpheuslummis.info
Advancing AI safety through convenings, coordination, software
https://orpheuslummis.info, based in Montréal
https://orpheuslummis.info, based in Montréal
Where is the People’s Consultation on AI ?
November 5, 2025 at 1:29 PM
Where is the People’s Consultation on AI ?
Reposted by Orpheus Lummis
This workshop follows one we ran in July, adding optional specialized talks, and light moderation in the breakout sessions. To see how that one went, and videos of the talks, see this thread:
www.lesswrong.com/posts/csdn3e...
www.lesswrong.com/posts/csdn3e...
Summary of our Workshop on Post-AGI Outcomes — LessWrong
Last month we held a workshop on Post-AGI outcomes. This post is a list of all the talks, with short summaries, as well as my personal takeaways. …
www.lesswrong.com
October 28, 2025 at 10:06 PM
This workshop follows one we ran in July, adding optional specialized talks, and light moderation in the breakout sessions. To see how that one went, and videos of the talks, see this thread:
www.lesswrong.com/posts/csdn3e...
www.lesswrong.com/posts/csdn3e...
Looking forward to the paper
October 24, 2025 at 3:37 PM
Looking forward to the paper
I found the video playlist! www.youtube.com/playlist?lis...
Post-AGI Civilizational Equilibria Workshop - YouTube
This workshop addressed the technical and institutional questions of how to safeguard human interests after AI surpasses human abilities. The development of ...
www.youtube.com
October 24, 2025 at 3:18 PM
I found the video playlist! www.youtube.com/playlist?lis...
Looking forward to the outputs of the workshop - recorded talks, etc?
October 24, 2025 at 3:16 PM
Looking forward to the outputs of the workshop - recorded talks, etc?
It would be great to hear more about the cooperation network and outcomes of the forum.
October 24, 2025 at 2:57 PM
It would be great to hear more about the cooperation network and outcomes of the forum.
just sharing some related papers:
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training arxiv.org/abs/2401.05566
- Here Comes The AI Worm arxiv.org/abs/2403.02817
- Many-shot Jailbreaking openreview.net/forum?id=cw5...
- PoisonedRAG arxiv.org/abs/2402.07867
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training arxiv.org/abs/2401.05566
- Here Comes The AI Worm arxiv.org/abs/2403.02817
- Many-shot Jailbreaking openreview.net/forum?id=cw5...
- PoisonedRAG arxiv.org/abs/2402.07867
Many-shot Jailbreaking
We investigate a family of simple long-context attacks on large language models: prompting with hundreds of demonstrations of undesirable behavior. This attack is newly feasible with the larger...
openreview.net
October 6, 2025 at 9:15 PM
just sharing some related papers:
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training arxiv.org/abs/2401.05566
- Here Comes The AI Worm arxiv.org/abs/2403.02817
- Many-shot Jailbreaking openreview.net/forum?id=cw5...
- PoisonedRAG arxiv.org/abs/2402.07867
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training arxiv.org/abs/2401.05566
- Here Comes The AI Worm arxiv.org/abs/2403.02817
- Many-shot Jailbreaking openreview.net/forum?id=cw5...
- PoisonedRAG arxiv.org/abs/2402.07867
looking forward to the lectures and perhaps to see more of its bibliography!
October 6, 2025 at 5:37 PM
looking forward to the lectures and perhaps to see more of its bibliography!